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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values or symbols associated with negativity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.81
     onData
    -0.81
    idać
    -0.76
    IUrlHelper
    -0.74
    fillType
    -0.73
    SharedCtor
    -0.72
    WithIOException
    -0.72
     AssemblyTitle
    -0.71
     pinulongan
    -0.71
    GEBURTSDATUM
    -0.71
    POSITIVE LOGITS
    Demografia
    0.65
     کیلومتر
    0.54
    Ouch
    0.50
    koľ
    0.49
     naturales
    0.47
    autoFocus
    0.47
    ichen
    0.46
    zzata
    0.46
     cherchez
    0.45
    ifu
    0.45
    Act Density 0.037%

    No Known Activations