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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations and related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     którzy
    -0.67
     quelli
    -0.60
    Два
    -0.57
     ktorí
    -0.57
     каждом
    -0.56
     Estos
    -0.55
     derniers
    -0.53
     estos
    -0.52
     kurie
    -0.52
     Один
    -0.52
    POSITIVE LOGITS
    Elles
    1.06
     Elles
    0.99
    她们
    0.93
     elles
    0.88
     celles
    0.88
    她們
    0.84
     lesquelles
    0.82
     ellas
    0.79
     kurios
    0.77
     éstas
    0.73
    Act Density 0.231%

    No Known Activations