INDEX
    Explanations

    pronouns or references to organizations

    references to groups or organizations involved in social justice issues

    New Auto-Interp
    Negative Logits
    amera
    -0.84
    emale
    -0.74
    osta
    -0.72
    ascal
    -0.71
    0000000000000000
    -0.69
    ðĿ
    -0.69
     hypoc
    -0.67
    redo
    -0.67
    acebook
    -0.66
    emort
    -0.65
    POSITIVE LOGITS
     Eid
    0.72
     upgr
    0.66
     Asgard
    0.66
     artific
    0.65
     Remastered
    0.64
     Adren
    0.64
    ãĥ¼ãĥĨ
    0.62
     Hitman
    0.61
    ãĥ¼ãĥ
    0.61
     smugg
    0.60
    Act Density 0.000%

    No Known Activations