OpenInterpretability
ストックにはログインが必要です
Open-source toolkit to audit what your LLM knows
Artificial Intelligence
Developer Tools
Open Source
The first mech interp toolkit that runs inside Claude Code, Cursor, and Cline via MCP. Production probes (FabricationGuard, agent-probe-guard) catch hallucinations + agent failures. ProbeBench leaderboard, SAE training from 30-min free Colab to paper-grade. Apache-2.0.
投票数: 0