INDEX
    Explanations

    information regarding violent incidents, such as altercations, shootings, accidents, and injuries

    incidents involving physical altercations or violence

    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.04
    3:0.05
    4:0.04
    5:0.05
    6:0.09
    7:0.11
    8:0.06
    9:0.08
    10:0.17
    11:0.09
    Negative Logits
    -1.31
     coined
    -1.28
    etheless
    -1.27
     philosoph
    -1.23
    enment
    -1.23
     Babel
    -1.20
     innov
    -1.19
     championed
    -1.18
    anguage
    -1.17
     Philos
    -1.15
    POSITIVE LOGITS
     burglary
    1.37
     misdemeanor
    1.36
    gew
    1.30
     felony
    1.30
    police
    1.30
     attacker
    1.29
     nearby
    1.28
     explosives
    1.26
    ilated
    1.25
    rouse
    1.24
    Act Density 0.711%

    No Known Activations