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

    Neuronpedia

    INDEX
    Explanations

    references to figures and citations in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     noting
    -0.56
     thinking
    -0.55
     considering
    -0.54
    lück
    -0.50
     thoughts
    -0.50
     saying
    -0.47
     thought
    -0.46
     note
    -0.45
     wondering
    -0.45
     stating
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.94
    parsedMessage
    0.91
    windowFixed
    0.87
    oredCriteria
    0.85
     TestBed
    0.84
     unknownFields
    0.82
    IsMutable
    0.79
    MigrationBuilder
    0.79
    setupUi
    0.79
    UnsafeEnabled
    0.78
    Act Density 0.082%

    No Known Activations