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

    Neuronpedia

    INDEX
    Explanations

    indicators of negative values or outcomes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.05
    setVerticalGroup
    -1.05
    IntoConstraints
    -0.95
     Paglinawan
    -0.93
    MLLoader
    -0.93
     nakalista
    -0.91
     nahilalakip
    -0.90
    makeConstraints
    -0.88
     الحره
    -0.87
     ویکی‌پدیا
    -0.87
    POSITIVE LOGITS
    </strong>
    0.50
    ’
    0.50
    .
    0.49
    -
    0.45
    </b>
    0.45
    ,
    0.44
    \
    0.44
    ;
    0.44
    V
    0.44
    برو
    0.43
    Act Density 0.004%

    No Known Activations