INDEX
    Explanations

    tokens representing the start of a document or section, indicated by a specific format

    New Auto-Interp
    Negative Logits
    ษา
    -0.58
     FormBuilder
    -0.55
    omiast
    -0.53
    Cordialement
    -0.52
     sạn
    -0.50
    PreAuthorize
    -0.50
     ControllerBase
    -0.49
     ejus
    -0.49
    ɹ
    -0.46
    __':
    
    -0.46
    POSITIVE LOGITS
     '\\;'
    0.87
     mergeFrom
    0.75
    Portály
    0.73
     Wikispecies
    0.70
     disambiguazione
    0.69
    Portail
    0.68
    OGND
    0.66
    TintMode
    0.66
    SharedDtor
    0.64
     AppCompatTheme
    0.63
    Act Density 0.134%

    No Known Activations