INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Vole
    -0.46
    ftest
    -0.45
     Vou
    -0.45
     Rope
    -0.43
    oup
    -0.43
    umn
    -0.43
    dok
    -0.42
    hnte
    -0.42
     vz
    -0.41
    arao
    -0.41
    POSITIVE LOGITS
    AndEndTag
    1.02
     typelib
    0.81
    UnusedPrivate
    0.79
     resourceCulture
    0.72
    contentLoaded
    0.71
    onAttach
    0.69
     مرئيه
    0.69
    Spoljašnje
    0.69
    featureID
    0.68
    <bos>
    0.67
    Act Density 0.029%

    No Known Activations