INDEX
    Explanations

    details related to physical harm or injury

    graphic descriptions of violence and injury

    New Auto-Interp
    Negative Logits
    ivals
    -0.91
    agents
    -0.82
     Families
    -0.75
     Income
    -0.70
    Reward
    -0.70
    actionDate
    -0.69
     Squadron
    -0.68
    edia
    -0.67
     Franch
    -0.67
    enario
    -0.65
    POSITIVE LOGITS
     protr
    1.11
     amput
    1.09
     numb
    1.06
     swollen
    1.00
     shaved
    0.96
     throb
    0.96
     abnorm
    0.93
     clenched
    0.84
     dors
    0.84
     thickness
    0.83
    Act Density 0.387%

    No Known Activations