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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and questions related to values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.79
     himſelf
    -0.76
    bibfield
    -0.75
    SEGUIR
    -0.73
     leſs
    -0.70
     itſelf
    -0.69
    aarrggbb
    -0.69
    titleMargin
    -0.69
    TypedDataSet
    -0.68
     iſt
    -0.67
    POSITIVE LOGITS
    :
    0.52
    \{\\
    0.47
    ,
    0.44
     "
    0.44
    fjspx
    0.43
     <<<<<<<<<<<<<<
    0.42
    ↵
    0.41
    ngdoc
    0.41
    —
    0.40
     “
    0.40
    Act Density 0.023%

    No Known Activations