mechinterp-runner

github:cesaregarza/SplatNLP · first committed 2025-12-08 · source · badge

Execute mechanistic interpretability experiments from JSON specs - family sweeps, itemsets, interactions, minimal cores, validation

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

3 commits to this file on GitHub (newest first).

2025-12-15 · commit bc86832 · Enhance mechinterp investigation and analysis capabilities

2025-12-11 · commit ee3ac52 · Enhance mechanistic interpretability documentation and introduce new patterns reference

2025-12-08 · commit 285383e · Add new skills and documentation for mechanistic interpretability