INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    K
    0.64
    ING
    0.64
    і
    0.63
    E
    0.59
    ۹
    0.57
    ing
    0.55
    0.54
    ܠ
    0.54
    ם
    0.52
    IA
    0.52
    POSITIVE LOGITS
    ل
    0.69
     with
    0.65
     on
    0.63
     On
    0.61
     for
    0.59
     Oni
    0.56
    1
    0.56
     For
    0.55
     Single
    0.55
     operands
    0.55
    Act Density 0.043%

    No Known Activations