INDEX
    Explanations

    terms related to law enforcement actions and incidents

    New Auto-Interp
    Negative Logits
     Bench
    -0.15
     bench
    -0.15
    اتÙĩ
    -0.15
    unya
    -0.15
    uch
    -0.14
     Halifax
    -0.14
    issan
    -0.13
     Bon
    -0.13
    th
    -0.13
     dating
    -0.13
    POSITIVE LOGITS
    readcr
    0.17
    FindObject
    0.16
    699
    0.16
    erken
    0.15
    razier
    0.15
    sburg
    0.14
    arken
    0.14
    celik
    0.14
    osi
    0.14
    ombat
    0.14
    Act Density 0.302%

    No Known Activations