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

    Neuronpedia

    INDEX
    Explanations

    Polish words and names, particularly those associated with geographical locations and personal identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.83
     cherchés
    -0.69
    oarece
    -0.61
    ziału
    -0.59
     سكانية
    -0.58
     każdym
    -0.57
     sobą
    -0.57
     дописавши
    -0.57
    ścia
    -0.56
     محفوظة
    -0.55
    POSITIVE LOGITS
     Pologne
    0.79
     Polish
    0.77
    Polish
    0.75
    Marcin
    0.71
     Marcin
    0.71
    Tomasz
    0.71
    Przypisy
    0.70
     Poland
    0.69
    Poland
    0.69
     ujednoznacz
    0.64
    Act Density 0.515%

    No Known Activations