concept
active
concept:counterfactual-maintenanceCounterfactual maintenance
The mental effort of holding models of how things could/should be different from actuality, contributing to compression stress.
Neighborhood — ranked by edge-count
Concepts (6)
concept
- Counterfactualrelated_toThe output value a model produces when an interchange intervention forces certain variables to take values from source inputs.
- Counterfactual Behaviorrelated_toThe behavior that would have occurred had the value of a causal variable been different while everything else remained the same; used as training labels in DAS/MAS.
- Counterfactual Staterelated_toThe state a neural network is placed in when its activations are modified via intervention
- Counterfactual Thinkingrelated_toEncoding possible future or alternative states; bioelectric patterns can represent an alternative morphological target even in an intact animal.
- Counterfactual claimsrelated_toTrue/false claims that a prompt edit shifts a behavior rate by at least 30pp; basis for all evaluation labels.
- Compression stressassociated_withThe ongoing cost of maintaining counterfactual aspects of experience, conflating 'what is', 'what could be', 'what should be', and 'what will be'.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Ability to entertain competing hypotheses within one inference engine; proposed hallmark of mindful inference
- Lens for evaluating explanations by whether they help predict behavior on counterfactual inputs.
- Auxiliary objective combining L2 and cosine losses against pre-recorded CL vectors to improve causal relevance when one model is causally inaccessible.
- Replace last-token code with target node.
- Auxiliary training objective from Grant (2025) that constrains intervened representations to remain near natural distribution
- Training models to answer Yes/No whether a prompt edit changes their behavior.
- MAS variant with an auxiliary CL loss objective for cases where one model is causally inaccessible, enabling ANN-BNN comparisons.