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

    Neuronpedia

    INDEX
    Explanations

    geographical location names, specifically cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.67
    protoimpl
    -0.67
    orde
    -0.67
     vistazo
    -0.63
    SourceChecksum
    -0.62
    FormState
    -0.61
    ThroughAttribute
    -0.61
     виправивши
    -0.61
    Vidite
    -0.60
    ковник
    -0.60
    POSITIVE LOGITS
     Мексичка
    0.87
     metropolitan
    0.86
    ADELPHIA
    0.83
     Chicago
    0.82
    Chicago
    0.78
    waukee
    0.77
     Angeles
    0.74
     Mumbai
    0.72
     London
    0.72
     Atlanta
    0.72
    Act Density 0.133%

    No Known Activations