INDEX
    Explanations

    references to historical and religious figures or events, particularly in a Christian context

    New Auto-Interp
    Negative Logits
     slu
    -0.15
     Strom
    -0.15
     Sle
    -0.15
    éru
    -0.15
     Kon
    -0.14
    994
    -0.14
    uario
    -0.13
     ÑģлÑĥ
    -0.13
    TRS
    -0.13
    æ´¥
    -0.13
    POSITIVE LOGITS
     Cruc
    0.25
     cruc
    0.23
     Pil
    0.22
     nailed
    0.22
     nails
    0.20
     Innoc
    0.18
    inn
    0.17
     cross
    0.17
     Cross
    0.17
     vinegar
    0.17
    Act Density 0.017%

    No Known Activations