INDEX
    Explanations

    references to sin and moral judgment

    New Auto-Interp
    Negative Logits
     للمعارف
    -0.75
    tagHelperRunner
    -0.74
    majánló
    -0.71
     ſeine
    -0.68
     Geiſt
    -0.67
     NSCoder
    -0.66
    MLLoader
    -0.66
    -0.65
     Geſch
    -0.64
    #+#
    -0.63
    POSITIVE LOGITS
     sin
    0.63
     sins
    0.60
     sinner
    0.59
     sinned
    0.57
     Sin
    0.52
     sinful
    0.52
     pecados
    0.49
    Sin
    0.49
     sinners
    0.46
     pecado
    0.44
    Act Density 0.275%

    No Known Activations