INDEX
    Explanations

    references to religious figures and their teachings

    New Auto-Interp
    Negative Logits
    .dm
    -0.15
     pent
    -0.15
    embr
    -0.15
    bullet
    -0.14
    edia
    -0.14
    ãĥ¼ãĥij
    -0.13
     Bakan
    -0.13
     captcha
    -0.13
    ActivityResult
    -0.13
    .mit
    -0.13
    POSITIVE LOGITS
     peace
    0.25
     صÙĦÙī
    0.21
    peace
    0.21
     Peace
    0.21
    Peace
    0.20
    (pb
    0.19
    WithMany
    0.18
    pb
    0.17
     pb
    0.17
     ÙĪØ³ÙĦÙħ
    0.17
    Act Density 0.092%

    No Known Activations