INDEX
    Explanations

    references to religious figures and practices

    New Auto-Interp
    Negative Logits
    vetica
    -0.15
    onders
    -0.15
    онÑĮ
    -0.14
     xu
    -0.14
    oes
    -0.14
    orget
    -0.14
    æĪ´
    -0.14
     sod
    -0.14
    oe
    -0.14
    OND
    -0.14
    POSITIVE LOGITS
    itori
    0.16
    InnerText
    0.15
    ppe
    0.15
    ëĿ
    0.14
    lte
    0.14
     tax
    0.14
    coli
    0.14
    ández
    0.14
     fore
    0.14
    ijo
    0.14
    Act Density 0.074%

    No Known Activations