logprob-prefill-analysis

【数据与研究】Reproduces the full prefill sensitivity analysis pipeline for reward hacking indicators. Use when evaluating how susceptible model checkpoints are to exploit-eliciting prefills, computing token-based trajectories, or comparing logprob vs token-count as predictors of exploitability.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准