INDEX
    Explanations

    references to police activity and incidents involving law enforcement

    New Auto-Interp
    Negative Logits
    kart
    -0.16
    elters
    -0.16
    odos
    -0.15
    št
    -0.15
    erno
    -0.15
    stalk
    -0.15
     Primitive
    -0.15
    ghi
    -0.14
    thic
    -0.14
    arking
    -0.14
    POSITIVE LOGITS
    esson
    0.15
    Ñij
    0.15
    462
    0.14
    bon
    0.14
    etto
    0.14
     insiders
    0.14
     insider
    0.14
     Chan
    0.13
    uns
    0.13
    awesome
    0.13
    Act Density 0.031%

    No Known Activations