INDEX
    Explanations

    references to groups of people or collective identities

    New Auto-Interp
    Negative Logits
     évêque
    -0.53
    droje
    -0.51
     אחרים
    -0.51
     esetén
    -0.49
     للمعارف
    -0.46
    APON
    -0.46
    CHELL
    -0.46
    -0.46
     natale
    -0.45
     Parigi
    -0.44
    POSITIVE LOGITS
     IBOutlet
    0.76
     Roskov
    0.75
    WebVitals
    0.69
     שוליים
    0.68
    tagHelperRunner
    0.64
     pips
    0.63
     createStore
    0.62
    tagext
    0.61
     فريبيس
    0.60
    ITECH
    0.59
    Act Density 0.261%

    No Known Activations