INDEX
    Explanations

    parts of words that may appear in names

    New Auto-Interp
    Negative Logits
    <bos>
    -1.23
     <=",
    -0.67
     disambiguazione
    -0.59
     مشين
    -0.58
     surla
    -0.57
     CreateTagHelper
    -0.57
    '
    -0.56
     ویکی‌پدی
    -0.54
    -0.52
     ujednoznacz
    -0.52
    POSITIVE LOGITS
     représenté
    0.61
    TagHelper
    0.60
    InSection
    0.57
     lạc
    0.57
     ainfi
    0.57
     Efq
    0.57
    κτηρισ
    0.55
     SafeArea
    0.55
     stessi
    0.55
     BorderSide
    0.54
    Act Density 0.392%

    No Known Activations