INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.59
     (
    -0.57
     $
    -0.50
    -0.49
      
    -0.49
    -0.47
     Lo
    -0.45
     lo
    -0.45
     "
    -0.44
     [
    -0.44
    POSITIVE LOGITS
     beginnetje
    1.11
     disambiguazione
    1.06
     itſelf
    1.05
    oredCriteria
    1.02
    InjectAttribute
    0.99
     Efq
    0.98
     Roskov
    0.96
     ویکی‌پدی
    0.94
     Anſ
    0.94
     Reſ
    0.94
    Act Density 0.026%

    No Known Activations