Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to completion or finishing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    supset
    -0.79
     Krä
    -0.77
    triangleq
    -0.75
    pyr
    -0.74
    ROLE
    -0.74
    reqs
    -0.73
    bytes
    -0.72
    MigrationBuilder
    -0.71
     Vallarta
    -0.71
    brigens
    -0.68
    POSITIVE LOGITS
     Finish
    1.67
     FINISH
    1.66
     finish
    1.65
    Finish
    1.53
    finish
    1.52
     finished
    1.52
     finishes
    1.50
    FINISH
    1.49
     Finished
    1.43
     finishing
    1.40
    Act Density 0.060%

    No Known Activations