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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Santa" and related place names

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.93
    ✨:
    -0.87
     مشين
    -0.86
     PMA
    -0.85
    例句
    -0.82
    出版年
    -0.81
    modelBuilder
    -0.78
     وتسجيلات
    -0.78
     ویکی‌پدی
    -0.77
    Хьажоргаш
    -0.76
    POSITIVE LOGITS
     Santa
    1.73
     SANTA
    1.59
    Santa
    1.57
     santa
    1.36
    SANTA
    1.31
    santa
    1.25
     Claus
    1.06
     Sante
    1.05
    サンタ
    0.86
     SANT
    0.79
    Act Density 0.008%

    No Known Activations