INDEX
    Explanations

    occurrences of police and legal terms related to crimes and incidents

    New Auto-Interp
    Negative Logits
     Ip
    -0.15
    ÄĽÅ¾
    -0.15
    iday
    -0.14
     heads
    -0.14
     steam
    -0.14
    fi
    -0.14
     Honest
    -0.14
     ý
    -0.14
    poz
    -0.13
     Future
    -0.13
    POSITIVE LOGITS
     release
    0.16
     prelim
    0.16
    /releases
    0.16
     reports
    0.15
     released
    0.15
     police
    0.15
    bsub
    0.15
    _softmax
    0.15
    Initial
    0.15
    ighbors
    0.15
    Act Density 0.074%

    No Known Activations