INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    s
    -0.75
    t
    -0.67
    d
    -0.60
    m
    -0.59
     Scripture
    -0.57
    sav
    -0.54
    nan
    -0.54
    system
    -0.53
    n
    -0.53
    sof
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.71
     Chwiliwch
    0.68
    WriteAttribute
    0.68
     виправивши
    0.68
    RefNanny
    0.65
     ComVisible
    0.64
    TagMode
    0.63
     einzu
    0.63
     "..\..\..\
    0.62
    ьаж
    0.60
    Act Density 0.058%

    No Known Activations