INDEX
    Explanations

    terms and phrases related to discrimination and social justice issues

    New Auto-Interp
    Negative Logits
    TagMode
    -0.69
    stateProvider
    -0.55
    Impl
    -0.54
    __':
    
    -0.53
    ]='\
    -0.52
    APTER
    -0.51
    .*")]
    -0.50
     forState
    -0.49
    PRWEB
    -0.49
    ]]=
    -0.49
    POSITIVE LOGITS
     perpetrated
    0.78
    TargetException
    0.70
    rrggbb
    0.68
     syndic
    0.66
     suç
    0.66
     raiſ
    0.63
     danni
    0.62
     chronique
    0.62
     druge
    0.62
     attacks
    0.60
    Act Density 0.382%

    No Known Activations