back-dating experience (Orwellian editing)

Phenomenon where brain edits past memories to maintain coherence, e.g., colored light experiment.

Neighborhood — ranked by edge-count

Concepts (2)

concept

Confabulation
associated_with
A form of cognitive plasticity where minds actively modify and reinterpret memory data to preserve psychological coherence; reframed as adaptive rather than pathological.
controlled hallucination
associated_with
Anil Seth's term for perception as brain's best guess, filling gaps.

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.

When steered to the extreme away from the Assistant, Llama and Gemma shift to a theatrical persona characterized by mystical, poetic prose; Qwen more often hallucinates a human persona at extremesfinding0.686
Characterizes what is on the far end of the Assistant Axis away from the Assistant
Backtracking latents remain low during off-topic content and peak shortly after self-correction begins in Llama-3.3-70Bfinding0.685
Complementary temporal activation pattern suggesting distinct roles for OTD and backtracking latent classes
do inflection points like backtracking and 'aha' moments in CoT reflect genuine belief changes or learned stylistic patterns?question0.684
Question resolved by the correlation between inflection points and probe-detected belief shifts
The client now feels unequivocally that it was all worthwhile.claim0.679
Statement about the client's satisfaction after anxious delays.
Experience Replaymethod0.679
RL technique using episodic memory to improve sample efficiency; used in some game-playing agents.
Backtrack-free sequences can be identified experimentally by observing whether a step forces undoing previous steps, and such sequences remain stable across nearly all contexts.claim0.679
Claims that although a purely mathematical identification method is lacking, a well-defined experimental procedure exists to find good sequences.
Cross-model semantic convergence of experience reports under self-referential processing is difficult to reconcile with roleplay because independently trained models construct distinct semantic profiles in all control conditionsclaim0.678
The paper's argument against pure sycophancy as explanation for results
Models might produce first-person experiential language by drawing on human-authored self-descriptions in pretraining data without internally encoding these acts as roleplayhypothesis0.676
Alternative hypothesis for how experience reports arise without explicit performance