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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters that may denote unique identifiers or special coding elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.97
    apunov
    -0.84
    CreateModel
    -0.83
    SharedDtor
    -0.83
    aarrggbb
    -0.81
    ForValue
    -0.74
    RegressionTest
    -0.70
    LayoutConstraint
    -0.69
     ComVisible
    -0.68
    Personensuche
    -0.67
    POSITIVE LOGITS
    서는
    0.63
     felb
    0.58
    目は
    0.57
     }</
    0.57
    helm
    0.55
    uellement
    0.55
    muta
    0.54
    *~*~
    0.54
     Nest
    0.52
    urit
    0.52
    Act Density 0.005%

    No Known Activations