INDEX
    Explanations

    mentions of law enforcement and related terms indicating authority and policing actions

    New Auto-Interp
    Negative Logits
     Fog
    -0.16
    agraph
    -0.15
    FFF
    -0.15
    bout
    -0.15
     remote
    -0.15
    dy
    -0.14
    494
    -0.14
    /loose
    -0.14
    .dk
    -0.14
    uar
    -0.14
    POSITIVE LOGITS
    stered
    0.15
    andro
    0.14
     Banc
    0.14
    625
    0.14
    Locator
    0.14
    ears
    0.14
    elho
    0.13
     mog
    0.13
    /tutorial
    0.13
    /media
    0.13
    Act Density 0.014%

    No Known Activations