INDEX
    Explanations

    references to religious practices and ceremonies

    New Auto-Interp
    Negative Logits
     å¦
    -0.16
     заÑģÑĤ
    -0.16
    ovah
    -0.15
     Canter
    -0.15
    رج
    -0.15
    ouver
    -0.15
     PLUGIN
    -0.14
    eldorf
    -0.14
    ennon
    -0.14
     Cush
    -0.14
    POSITIVE LOGITS
     baptism
    0.34
     Bapt
    0.31
     bapt
    0.28
     baptized
    0.23
     Bat
    0.21
     sponsors
    0.20
     bat
    0.20
     font
    0.19
     dunk
    0.19
     immersion
    0.19
    Act Density 0.052%

    No Known Activations