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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment related to legal matters or disputes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.49
    um
    -0.48
     Picchu
    -0.47
     herbic
    -0.45
    StructEnd
    -0.45
    BuildContext
    -0.44
     refleja
    -0.42
     freg
    -0.42
     vainilla
    -0.41
    é
    -0.41
    POSITIVE LOGITS
    esez
    0.75
     Мексичка
    0.71
     HasFactory
    0.71
    Pautan
    0.71
    saraba
    0.69
     تضيفلها
    0.69
     समीक्षक
    0.67
    cyclopedia
    0.66
     fieldNum
    0.66
    ratulations
    0.65
    Act Density 0.003%

    No Known Activations