INDEX
    Explanations

    foreign words and suffixes

    New Auto-Interp
    Negative Logits
     a
    0.71
    A
    0.67
     A
    0.66
     I
    0.61
     (
    0.60
    matic
    0.56
    ENSIONS
    0.54
    $,
    0.53
    ses
    0.52
     Championships
    0.48
    POSITIVE LOGITS
    and
    0.95
     and
    0.80
    x
    0.76
    0.74
    ق
    0.73
    0.72
    จะ
    0.72
    0.71
    ة
    0.70
    ing
    0.69
    Act Density 0.204%

    No Known Activations