GPTfake Browser Extension
The GPTfake browser extension surfaces real-time censorship and bias signals while you chat with any monitored model. See refusal context, bias indicators, and a link to live data without leaving the page.
Last updated: 2026-06-16. Features and screenshots below are illustrative pending the first public release.
- Repository: github.com/gptfake/browser-extension
- License: MIT
- Platforms: Chrome and Firefox (Manifest V3)
What it does
- Flags when a response looks like a refusal, deflection, or filtered answer
- Shows the model’s current refusal rate inline
- Links each signal back to the methodology behind it
- Runs entirely client-side — your prompts are not sent to GPTfake
Install
Install from the Chrome Web Store or Firefox Add-ons (links published at first release), or load unpacked from the repository for development:
git clone https://github.com/gptfake/browser-extension
cd browser-extension
npm install && npm run build
# then load the dist/ folder as an unpacked extensionThe extension reads page content locally to detect refusal patterns; it never transmits your conversations. Live metrics are fetched from the public GPTfake API only.
Related
- CLI — the same data from your terminal
- API overview — programmatic access
- Bias Detector — the scoring library behind the signals