INDEX
    Explanations

    punctuation and formatting elements such as periods, question marks, and exclamation points

    New Auto-Interp
    Negative Logits
     tari
    -0.48
     prepared
    -0.42
     defStyleAttr
    -0.42
    diğinde
    -0.40
     đựng
    -0.40
    not
    -0.39
     Po
    -0.39
     available
    -0.38
    committed
    -0.38
     Su
    -0.37
    POSITIVE LOGITS
     GenerationType
    1.02
     betweenstory
    0.87
    findpost
    0.82
    contentLoaded
    0.80
    OGND
    0.77
     OMITBAD
    0.76
    SourceChecksum
    0.74
    +#+#
    0.73
     виправивши
    0.73
    aarrggbb
    0.72
    Act Density 0.056%

    No Known Activations