INDEX
    Explanations

    references to violence and its impact

    New Auto-Interp
    Negative Logits
    MathML
    -0.37
     skry
    -0.37
     abordar
    -0.36
    rachtet
    -0.36
    span
    -0.34
    IContainer
    -0.34
     industry
    -0.33
     zeros
    -0.33
    EMOS
    -0.33
     Nähe
    -0.32
    POSITIVE LOGITS
     Picture
    0.74
     ProtoMessage
    0.72
     peaceful
    0.70
    peaceful
    0.68
     Pic
    0.67
     OMITBAD
    0.65
    Picture
    0.65
    Peaceful
    0.65
     violent
    0.65
     Pics
    0.64
    Act Density 0.187%

    No Known Activations