INDEX
    Explanations

    references to specific religious communities and their members

    New Auto-Interp
    Negative Logits
    iane
    -0.15
    irsch
    -0.15
     Laden
    -0.15
    ãİ¡
    -0.14
    igg
    -0.14
    meldung
    -0.13
    ilir
    -0.13
    окÑĥ
    -0.13
     Parts
    -0.13
     Tavern
    -0.13
    POSITIVE LOGITS
     spin
    0.15
     Colum
    0.14
    _flutter
    0.14
    osp
    0.14
    spin
    0.14
    úi
    0.14
    à¤łà¤¨
    0.14
    çĽĬ
    0.14
    adel
    0.14
     Hosp
    0.14
    Act Density 0.035%

    No Known Activations