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

    Neuronpedia

    INDEX
    Explanations

    evaluative phrases that assess performance or well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zub
    -0.54
     Quảng
    -0.53
     brev
    -0.52
     collector
    -0.51
     Chrift
    -0.51
    acherous
    -0.50
    Endless
    -0.49
    isset
    -0.49
     dosp
    -0.49
     Identifier
    -0.48
    POSITIVE LOGITS
     fared
    0.88
    MigrationBuilder
    0.70
    ConstraintMaker
    0.70
     behaving
    0.70
     zure
    0.68
    RenderAtEndOf
    0.67
     mergeFrom
    0.66
     للمعارف
    0.66
     réuss
    0.65
     kasarigan
    0.64
    Act Density 0.405%

    No Known Activations