Mechanistic interpretability is defined as producing model-level, ontic, causal-mechanistic, falsifiable explanations, and a new 'Explanatory Optimism' conjecture is introduced as a necessary precondition for its success.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i
Mechanistic interpretability is defined as producing model-level, ontic, causal-mechanistic, falsifiable explanations, and a new 'Explanatory Optimism' conjecture is introduced as a necessary precondition for its success.