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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     상세
    -0.46
     ex
    -0.42
    tés
    -0.42
     tay
    -0.41
     ver
    -0.41
    gris
    -0.40
     o
    -0.40
    wers
    -0.40
    ナル
    -0.40
     ο
    -0.39
    POSITIVE LOGITS
    DockStyle
    0.83
    клопе
    0.82
     الحره
    0.81
    DoubleQuotes
    0.80
    UnsafeEnabled
    0.73
    WireFormatLite
    0.70
    TemporalType
    0.70
    endphp
    0.69
    ]")]
    0.68
    IntoConstraints
    0.67
    Act Density 0.117%

    No Known Activations