Pinned Loading

1. llm-attacks/llm-attacks llm-attacks/llm-attacks Public

   Universal and Transferable Attacks on Aligned Language Models

   Python 4.6k 615

2. representation-engineering representation-engineering Public

   Representation Engineering: A Top-Down Approach to AI Transparency

   Jupyter Notebook 970 124

3. autocast autocast Public

   Forecasting Future World Events with Neural Networks (NeurIPS 2022)

   Jupyter Notebook 186 49

4. hendrycks/test hendrycks/test Public

   Measuring Massive Multitask Language Understanding | ICLR 2021

   Python 1.6k 115

5. pixmix pixmix Public

   PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)

   Python 110 10

6. aypan17/machiavelli aypan17/machiavelli Public

   Python 147 35