INDEX
    Explanations

    references to various religious and ethnic communities

    New Auto-Interp
    Negative Logits
    gren
    -0.16
    gest
    -0.13
    VOKE
    -0.13
     Flour
    -0.13
    PEAR
    -0.13
    lain
    -0.13
    gers
    -0.13
    ged
    -0.13
    river
    -0.13
    utter
    -0.13
    POSITIVE LOGITS
    íijľ
    0.16
    हन
    0.16
    /fw
    0.16
    epy
    0.15
    inden
    0.15
     Owned
    0.14
    æĮ¯ãĤĬ
    0.14
    fea
    0.14
    ippi
    0.14
    -Owned
    0.14
    Act Density 0.106%

    No Known Activations