INDEX
    Explanations

    discussions related to social justice and equity

    New Auto-Interp
    Negative Logits
    bia
    -0.16
    ibern
    -0.15
     Geile
    -0.15
    abel
    -0.15
     Blick
    -0.15
    èĵ
    -0.14
    elman
    -0.14
    bud
    -0.14
    èĽĽ
    -0.14
     ÙħÛĮÙĦ
    -0.14
    POSITIVE LOGITS
     Airways
    0.14
    EXPR
    0.14
     blah
    0.13
    大人
    0.13
     showDialog
    0.13
     caric
    0.13
     è¢
    0.13
    odzi
    0.12
    America
    0.12
    &q
    0.12
    Act Density 0.095%

    No Known Activations