Normalized Indirect Effect (NIE)

Metric for causal intervention experiments: 0 = wholly ineffective intervention, 1 = intervention causes model to label false statements as TRUE with the same confidence as genuine true statements

Neighborhood — ranked by edge-count

Papers (1)

paper

The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
introduces

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Normalized Indirect Effectmethod0.880
Metric for intervention effectiveness: 0 = ineffective, 1 = full flip of model output from false to true or vice versa
EI and normalized EI could serve as a unified metric for out-of-distribution generalization.claim0.706
Conjecture that maximizing EI yields causal representations invariant to distribution shifts.
What Is The Nature Of The Effects Thatquestion0.695
Mass-mean probe directions outperform LR and CCS in causal intervention experiments (NIE) in 7/8 experimental conditionsfinding0.691
Core result showing MM is superior to LR for causal implication despite similar classification accuracy
The results generalise readily to non-equilibrium systems where scaling relationships remain similar (e.g., dynamic or localised scaling).claim0.690
Claim about broader applicability of the scaling argument
Effect Coefficient (Eff)concept0.689
Normalized EI bounded 0-1, decomposed into determinism minus degeneracy.
Natural Inductionconcept0.686
Emerging framework that seeks invariants between evolution and learning; cited as future direction.
EVEE provides mechanistic explanations for variant effects derived from model internals, not just pathogenicity calls.claim0.683
Core interpretability claim distinguishing EVEE from black-box prediction tools; applies interpretability for science.