# AI Content Detector — Perplexity and Burstiness, Measured Locally

> Score text with a real language model in your browser and see the per-token surprise that detection methods are built on.

This detector runs a real language model over your text in your browser and reports the two measurements published detection methods are built on: perplexity, the average surprise the model felt at each token, and burstiness, how much that surprise varied between sentences. Generated text tends to be less surprising and more evenly so. It reports the numbers and refuses to issue a verdict, because stylometric detection cannot establish authorship.

**URL:** https://convertto.tech/t/ai-content-detector
**Category:** On-Device AI (https://convertto.tech/c/local-ai-tools)
**Privacy:** Runs entirely in the browser; no upload
**Cost:** Free, no sign-up
**Last updated:** 2026-08-01

## Key facts

- **Method:** Per-token log-probability from a language model — perplexity and burstiness
- **Scoring model:** GPT-2 (124M) — a 267 MB one-time download, then run on your device
- **Uploads:** None — the text never leaves your browser
- **Verdict:** None issued. The measurements are reported with their limits
- **Privacy:** Runs entirely in your browser — nothing is uploaded
- **Cost:** Free, unlimited, no sign-up

## How to use

1. Enter or paste your text.
2. Press Run, then download the result when it is ready.

## FAQ

### Can this prove text was written by AI?

No. No detector can, including the paid ones that quote a confident percentage. Perplexity measures how predictable text is to a language model, and clear, conventional, well-edited human writing is also predictable — that is what makes it clear. The measurement is real; the inference from it to authorship is not sound.

### Why do you not show a percentage?

Because a percentage implies a calibrated probability, and there is no calibration behind it. People are failed, disciplined and fired on the strength of those numbers. Showing the underlying measurements against their baselines lets you interrogate the reading instead of deferring to it.

### What is perplexity?

The exponential of the average negative log-probability the model assigned to each actual token — in plain terms, how surprised it was. Low perplexity means the text went the way the model expected. Generated text tends to be low because it was produced by maximising exactly that predictability.

### What is burstiness?

The variation in perplexity from sentence to sentence. Human writing lurches: an ordinary sentence, then a strange one, then a digression. Sampling from a probability distribution produces a flatter profile. Burstiness is the more durable of the two signals because it survives light editing.

### Why does it flag my writing as AI?

Most likely because it is clear and conventional. Technical documentation, legal text, formal academic prose and writing by non-native English speakers all score as predictable. Published research specifically found elevated false-positive rates for non-native writers — that is a property of the method, and the reason this tool refuses to convert its numbers into an accusation.

### Which model does the scoring?

GPT-2, because it is small enough to run in a browser and is what most published detection work is calibrated against. It is a weak proxy for what a current frontier model finds predictable, so recent model output separates less cleanly than the original papers suggest. Treat the numbers as descriptive, not diagnostic.

## Sources

- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://arxiv.org/abs/2301.11305) — arXiv
- [GPT detectors are biased against non-native English writers](https://arxiv.org/abs/2304.02819) — arXiv

## Related tools

- [AI Writing Pattern Checker](https://convertto.tech/t/ai-writing-pattern-checker): Measure sentence-length variance, vocabulary richness, marker phrases and typographic tells, with per-sentence scoring.
- [Keyword Density Checker](https://convertto.tech/t/keyword-density-checker): Analyse which words and phrases dominate your content, and how often they appear.
- [Letter Frequency Analyser](https://convertto.tech/t/letter-frequency-analyser): Count letter and character frequencies — useful for cryptograms and puzzle solving.
- [Log File Parser](https://convertto.tech/t/log-parser): Parse Apache, Nginx or JSON log lines into a sortable table with traffic summaries.
- [Word & Character Frequency Counter](https://convertto.tech/t/text-statistics): Count how often each word, character or line appears in your text.
- [Word Frequency Counter](https://convertto.tech/t/word-frequency-counter): Count how often each word appears, with stop-word filtering and a frequency chart.
- [AI Alt Text Generator](https://convertto.tech/t/ai-alt-text-generator): Describe an image with a captioning model running in your browser — a first draft for the alt attribute you then edit.
- [AI Audio Transcription](https://convertto.tech/t/ai-audio-transcription): Run Whisper locally to turn speech into text, SRT, VTT or a timestamped transcript. Works offline after the first run.