INDEX
    Explanations

    references to nations and national identity

    New Auto-Interp
    Negative Logits
     Ãľl
    -0.17
    DataStream
    -0.16
    .gwt
    -0.14
    é»
    -0.14
    .Dao
    -0.14
    lady
    -0.14
    aky
    -0.14
    kip
    -0.14
    ãĤº
    -0.14
    ytt
    -0.14
    POSITIVE LOGITS
    foil
    0.15
    æ£ļ
    0.15
    å¹»
    0.15
    ıza
    0.15
    adera
    0.15
     blind
    0.14
    neas
    0.14
    onym
    0.14
     Lik
    0.14
    aran
    0.14
    Act Density 0.040%

    No Known Activations