INDEX
    Explanations

    events related to crime and violence

    New Auto-Interp
    Negative Logits
    uzzi
    -0.16
    rophy
    -0.16
    LayoutConstraint
    -0.16
    orget
    -0.16
     Prev
    -0.15
    /fw
    -0.15
    785
    -0.14
     hum
    -0.14
    vider
    -0.14
    permanent
    -0.14
    POSITIVE LOGITS
    yar
    0.15
    thumbnail
    0.14
    usra
    0.14
     law
    0.14
     
    0.14
    183
    0.14
    dance
    0.14
     pán
    0.13
     Mir
    0.13
     EOF
    0.13
    Act Density 0.030%

    No Known Activations