Causal Decoupling

Emergent causation where macro-variable has causal influence on its own future independently of micro-states.

Neighborhood — ranked by edge-count

concept

Causal Emergence
associated_with
Core concept: degree to which an agent exerts unique predictive power on its future; key to cognition at all scales.
Synergistic Information
associated_with
Information-theoretic measure (Edlund et al.) characterizing interdependencies in agent-environment systems.

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.

Causal Mediationconcept0.775
Whether an internal direction causally controls a target behavior, verified by intervention success
Causal Scrubbingmethod0.769
Method by Chan et al. 2022 for rigorously testing interpretability hypotheses via interventions
Constructive Causal Abstractionconcept0.760
Formal definition: H is a constructive abstraction of L under alignment Π when interchange interventions have equivalent effects at both levels.
Causal informational couplingconcept0.759
Operational definition of introspection: self-report covaries monotonically with probe-defined direction AND causally shifting activations shifts the report in a semantically coherent way
Causal Mechanismconcept0.759
Function determining the value of a variable based on its causal parents in an acyclic causal model.
Causal Invarianceconcept0.758
Property that causal mechanisms remain stable across environments; desirable for OOD.
Causal abstractionconcept0.757
A framework the paper uses alongside feature geometry to deepen mechanistic understanding of LMs
causal bypassingconcept0.749
Confound where naming injected concepts reflects direct logit effects rather than metacognitive awareness, raised by Morris & Plunkett