INDEX
    Explanations

    references to religious groups and community structures

    New Auto-Interp
    Negative Logits
    ilir
    -0.16
    ãİ¡
    -0.15
    irsch
    -0.14
    ruba
    -0.14
    ãĥ³ãĥĦ
    -0.14
    lfw
    -0.14
    zy
    -0.13
    itz
    -0.13
    wers
    -0.13
    aney
    -0.13
    POSITIVE LOGITS
    γη
    0.17
    _iff
    0.14
    ÅĦ
    0.14
    еÑĤÑĮÑģÑı
    0.14
     prol
    0.13
    aphore
    0.13
    (targetEntity
    0.13
    odule
    0.13
    -floating
    0.13
    жи
    0.13
    Act Density 0.065%

    No Known Activations