INDEX
    Explanations

    incidents of violent crime and their contexts

    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.67
    хьтан
    -0.56
     تانيه
    -0.55
    aspetto
    -0.55
    Personensuche
    -0.53
    [::-
    -0.53
    Encyklopedia
    -0.52
    Vidite
    -0.52
     pinulongan
    -0.49
     incor
    -0.49
    POSITIVE LOGITS
    ruptedException
    0.62
     disponibilités
    0.52
    nuff
    0.51
    ylvania
    0.51
     anoche
    0.48
     efectivos
    0.47
    tweet
    0.47
    brać
    0.46
     Enforcement
    0.45
    NewUrlParser
    0.45
    Act Density 0.185%

    No Known Activations