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

    Neuronpedia

    INDEX
    Explanations

    exclamation marks and their significance in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    :
    -0.63
     TestBed
    -0.57
     publish
    -0.53
     onOptions
    -0.53
    :"",
    -0.52
    2
    -0.51
     =
    -0.50
    int
    -0.50
     &
    -0.50
    ’
    -0.50
    POSITIVE LOGITS
    MigrationBuilder
    0.96
     مشين
    0.86
     ModelExpression
    0.83
     المعيارى
    0.83
     ویکی‌پدیای
    0.82
    ="@+
    0.81
     فريبيس
    0.80
    uxxxx
    0.80
     nakalista
    0.79
     contextLoads
    0.77
    Act Density 0.001%

    No Known Activations