Trending repositories: interpretability

1 tracked repository tagged with interpretability, ordered by stars. Use the topic filters below to narrow further.

Filter by topic

1 of 1 repository

  • p-e-w/heretic

    Fully automatic censorship removal for language models

    AI summary: Fully automatic censorship removal tool for transformer-based language models using directional ablation.

    31,031ai-mlPythonAGPL-3.0