INDEX
    Explanations

    terms and phrases related to discrimination and civil rights violations

    New Auto-Interp
    Negative Logits
    ORIZ
    -0.15
    ĮĢ
    -0.15
    lify
    -0.15
    emo
    -0.15
    lier
    -0.15
    ATOM
    -0.14
    Ļ
    -0.14
     Rap
    -0.14
    liers
    -0.14
    long
    -0.13
    POSITIVE LOGITS
    uzzi
    0.16
     Hizmet
    0.16
    phies
    0.15
    éģ£
    0.15
    ¦¬
    0.14
    .ObjectModel
    0.14
    viÄį
    0.14
    751
    0.14
    à¥įवव
    0.14
    erence
    0.14
    Act Density 0.020%

    No Known Activations