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

    Neuronpedia

    INDEX
    Explanations

    instances of specific formatting or symbolic representations in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.85
    SequentialGroup
    -0.78
    SharedDtor
    -0.73
    Personensuche
    -0.69
    __':
    -0.62
    XmlType
    -0.59
    $}
    -0.58
    ValueStyle
    -0.57
    Lähteet
    -0.56
    Boli
    -0.56
    POSITIVE LOGITS
    sizeCache
    0.56
    ówn
    0.54
    bör
    0.52
    μφωνα
    0.52
     Jams
    0.52
     renon
    0.52
     Justus
    0.51
    CJK
    0.50
    oredCriteria
    0.50
     kár
    0.49
    Act Density 0.021%

    No Known Activations