INDEX
    Explanations

    references to incidents involving guns and shootings

    New Auto-Interp
    Negative Logits
    hton
    -0.15
    estone
    -0.15
    aben
    -0.15
    ensible
    -0.14
    ylko
    -0.14
    #__
    -0.14
    itia
    -0.14
    ære
    -0.13
    psc
    -0.13
    emouth
    -0.13
    POSITIVE LOGITS
    oker
    0.15
     pij
    0.14
    TestingModule
    0.14
    MUX
    0.14
     Machinery
    0.14
     Jays
    0.13
    ãĥ
    0.13
     dÃ¼ÅŁÃ¼r
    0.13
    .Pointer
    0.13
     Recorder
    0.13
    Act Density 0.156%

    No Known Activations