INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    The
    -1.37
     The
    -1.24
    .
    -0.88
    ,
    -0.87
     the
    -0.82
     THE
    -0.75
     and
    -0.73
    This
    -0.73
    ;
    -0.69
     (
    -0.67
    POSITIVE LOGITS
    GEBURTSDATUM
    1.58
     disambiguazione
    1.54
     GenerationType
    1.31
     незавершена
    1.31
     autorytatywna
    1.30
    verwijspagina
    1.30
    fjspx
    1.30
     snippetHide
    1.28
     Мексичка
    1.26
     nahilalakip
    1.23
    Act Density 0.216%

    No Known Activations