INDEX
    Explanations

    events involving violence or conflict

    New Auto-Interp
    Negative Logits
    emouth
    -0.18
    zon
    -0.17
    mlink
    -0.17
    ĺ
    -0.16
    Disposition
    -0.16
    istle
    -0.15
    umpt
    -0.15
    upe
    -0.14
    UnderTest
    -0.14
    PropertyChanged
    -0.14
    POSITIVE LOGITS
     Heck
    0.15
     heck
    0.15
     ag
    0.14
     epith
    0.14
     bear
    0.14
    bear
    0.14
     mob
    0.14
    ivial
    0.14
     mess
    0.14
     demand
    0.14
    Act Density 0.221%

    No Known Activations