INDEX
    Explanations

    mentions of police investigations and law enforcement actions

    New Auto-Interp
    Negative Logits
     fle
    -0.14
     Rouge
    -0.14
    Ñľ
    -0.13
     shooters
    -0.13
    aģı
    -0.13
    EMPL
    -0.13
    .opensource
    -0.13
    nem
    -0.13
    Į
    -0.13
    çļ
    -0.13
    POSITIVE LOGITS
    orus
    0.15
    isco
    0.14
    _FORCE
    0.14
    asto
    0.14
    aston
    0.14
    _lc
    0.14
     çıkart
    0.14
    POST
    0.14
    prene
    0.13
    jad
    0.13
    Act Density 0.034%

    No Known Activations