INDEX
    Explanations

    actions or events associated with harm or violence

    New Auto-Interp
    Negative Logits
    れません
    -0.49
     تانيه
    -0.48
     numberWith
    -0.47
    colata
    -0.46
    دیگر
    -0.46
     Bourgoin
    -0.46
    thanol
    -0.45
    équi
    -0.45
     HttpClient
    -0.45
    судар
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.80
    annica
    0.70
    rungsseite
    0.69
    0.69
    IMPORTED
    0.67
    Chop
    0.66
    migrationBuilder
    0.65
    '));
    
    0.64
     Chop
    0.62
    %=
    0.61
    Act Density 0.104%

    No Known Activations