incoherence

Nonsensical or unphysical model outputs that result when interventions cross voids in activation space.

Neighborhood — ranked by edge-count

claim

Linear interventions across voids in activation space produce incoherent output, while following the manifold curve produces smooth control.
cites
General principle derived from the Mountain Car experiment: curved manifold-following yields coherent manipulation, linear shortcuts fail.

finding

In the Mountain Car case study, car position is a 1D manifold; linear interventions cross voids causing incoherence; following the 1D curve produces smooth control.
cites
Empirical demonstration that a semantically meaningful variable is encoded as a curved manifold, and that respecting its geometry is critical for effective intervention.

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.

Incommensurabilityconcept0.771
Kuhn's concept: the inability of ideas from one paradigm to be translated into the terms of another, causing communication breakdowns.
Coherenceconcept0.765
A property that makes a segment of space stand out as a center; determined by symmetry, connectedness, convexity, etc.
ambiguityconcept0.746
Multiple possible meanings for words like Alice, disambiguated by context; harder when grammar and meaning intertwine
irregularity in arrangementconcept0.739
Non-uniform placement, like cars parked irregularly, that increases relationship and life.
"For interpretability, I don't think we even have the right definitions."quote0.738
Ian Goodfellow quote used to illustrate the pre-paradigmatic state of interpretability research
nondeterminismconcept0.738
Inherent in Linda because an in statement chooses one matching tuple arbitrarily; essential for many parallel patterns.
Corrigibilityframework0.736
The property of an AI being safe to shut down or modify; discussed in context of GPT.
Impermanenceconcept0.735