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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.76
    ra
    1.73
    p
    1.68
    el
    1.56
    le
    1.53
    a
    1.52
    ing
    1.47
     (
    1.43
    al
    1.39
    x
    1.34
    POSITIVE LOGITS
    ین
    1.41
    ி
    1.23
     می‌کند
    1.14
     فونبټ
    1.12
     می‌شود
    1.09
     می‌کن
    1.09
     бесплат
    1.08
     بیاکت
    1.08
    dır
    1.07
    ામ
    1.05
    Act Density 0.000%

    No Known Activations