Mechanistic Interpretability on Federico Torriellihttps://federicotorrielli.github.io/tags/mechanistic-interpretability/Recent content in Mechanistic Interpretability on Federico TorrielliHugo -- 0.152.2enMon, 25 May 2026 00:00:00 +0000Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internalshttps://federicotorrielli.github.io/papers/activation-oracles-calibration/Mon, 25 May 2026 00:00:00 +0000https://federicotorrielli.github.io/papers/activation-oracles-calibration/A study of uncertainty quantification and calibration methods for activation oracles used to interpret language-model internals. Preprint on arXiv.