INDEX
    Explanations

    incidents related to violence or crime against individuals or groups

    New Auto-Interp
    Negative Logits
     Thorn
    -0.16
    atta
    -0.16
    otte
    -0.15
    egis
    -0.15
    DeltaTime
    -0.15
    mand
    -0.14
     diner
    -0.14
    479
    -0.14
    iser
    -0.14
    855
    -0.14
    POSITIVE LOGITS
     Citation
    0.16
    OnError
    0.15
    emade
    0.14
    cac
    0.14
    itez
    0.14
    mos
    0.14
    ">//
    0.14
     Outs
    0.14
    shi
    0.14
    üss
    0.14
    Act Density 0.035%

    No Known Activations