INDEX
    Explanations

    details related to violent incidents and law enforcement actions

    New Auto-Interp
    Negative Logits
    kok
    -0.15
    Ïĥη
    -0.14
    ATUS
    -0.14
     revealing
    -0.14
    éĻ
    -0.14
    FullYear
    -0.13
    fila
    -0.13
    urgeon
    -0.13
     Debugger
    -0.13
     sotto
    -0.13
    POSITIVE LOGITS
    970
    0.15
    ******↵
    0.14
     Wick
    0.14
    emma
    0.14
    achel
    0.14
    rips
    0.13
    ongan
    0.13
    oun
    0.13
    ivities
    0.13
     Yesterday
    0.13
    Act Density 0.027%

    No Known Activations