Stroop Task

Used to produce response conflict in ACC conflict monitoring studies

Neighborhood — ranked by edge-count

concept

Conflict Monitoring
implements
The ACC's detection of response conflict, shown to be constitutively emotional rather than purely cognitive

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.

Task Difficultyconcept0.726
The paper identifies task difficulty as a key moderator: easy MMLU questions show performative CoT, hard GPQA-Diamond questions show genuine reasoning
Task balancingconcept0.718
The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.
Task-specific parameterconcept0.711
Parameter specific to each task, e.g., task head.
Sentence Localization Taskmethod0.697
Novel task asking which of 10 sentences received injection, cycling injection through all positions to average out positional bias
Strength Comparison Taskmethod0.697
Novel task asking which of two sentences received a stronger injection, using matched-pairs design to control for positional bias
task generalizationconcept0.689
The ability to generalize across tasks; lacking in latent methods.
Next-Day Arithmetic Taskmethod0.688
The evaluation task used to probe Llama's representation of days of the week: questions of the form 'What day comes N days after X?'
Hinting Taskmethod0.686
One of four ToM tasks analyzed; requires inferring speaker intent from indirect hints; scored 0/1.