INDEX
    Explanations

    references to police interactions and calls for law enforcement

    New Auto-Interp
    Negative Logits
    ortex
    -0.14
    ãģŁãģĦ
    -0.14
    ÑģÑĤи
    -0.14
    unma
    -0.14
     fich
    -0.14
     Hire
    -0.13
     ><?
    -0.13
    ortion
    -0.13
     spect
    -0.13
    NSUserDefaults
    -0.13
    POSITIVE LOGITS
    \d
    0.16
     اÙĦÙħÙĪØ³
    0.15
    ioni
    0.14
    verb
    0.14
    ikat
    0.14
    vailability
    0.14
    chw
    0.14
    ucht
    0.14
    å½
    0.13
     Chamber
    0.13
    Act Density 0.050%

    No Known Activations