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

    Neuronpedia

    INDEX
    Explanations

    references to Poland and its historical or geographical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     cherchés
    -0.79
    ᅠ
    -0.74
     Verk
    -0.72
     /\.
    -0.71
    EnableWeb
    -0.71
     Banjar
    -0.71
     rozwo
    -0.70
    edip
    -0.69
     sobą
    -0.68
     Haarlem
    -0.68
    POSITIVE LOGITS
     Polish
    0.99
     Poland
    0.94
    Poland
    0.93
    Polish
    0.92
     Pologne
    0.92
     Lewandowski
    0.86
     Поль
    0.79
     Marcin
    0.77
     poland
    0.76
     Polonia
    0.75
    Act Density 0.089%

    No Known Activations