INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    )++;
    -0.71
     PopupWindow
    -0.68
     дописавши
    -0.63
     itſelf
    -0.63
     myſelf
    -0.63
    thâu
    -0.63
    UnknownFieldSet
    -0.62
    UserScript
    -0.62
    ństw
    -0.61
     estimés
    -0.60
    POSITIVE LOGITS
     for
    0.59
     the
    0.56
     to
    0.56
    s
    0.56
    a
    0.52
    GraphicsUnit
    0.50
    יך
    0.48
     that
    0.47
     kerül
    0.46
    0.46
    Act Density 0.203%

    No Known Activations