INDEX
    Explanations

    references to religious rituals and sacraments

    New Auto-Interp
    Negative Logits
     pe
    -0.16
     curves
    -0.14
     ir
    -0.14
    еÑĢо
    -0.14
    ree
    -0.14
     attention
    -0.14
    rees
    -0.14
     prom
    -0.14
     resc
    -0.14
     Sphere
    -0.14
    POSITIVE LOGITS
    uchar
    0.18
    óst
    0.16
     participation
    0.16
    é¤
    0.15
    vro
    0.14
     Participation
    0.14
    /table
    0.14
    ndef
    0.14
    fragistics
    0.14
    ymm
    0.14
    Act Density 0.008%

    No Known Activations