INDEX
    Explanations

    references to Islamic religious practices and figures

    New Auto-Interp
    Negative Logits
    ote
    -0.16
     shade
    -0.15
     crash
    -0.15
     Raymond
    -0.14
    525
    -0.14
    ur
    -0.14
     ray
    -0.14
     Crash
    -0.14
     Judges
    -0.14
     DAR
    -0.14
    POSITIVE LOGITS
    léd
    0.16
    Equals
    0.15
    igan
    0.15
    enler
    0.15
    리ìĸ´
    0.15
    kelig
    0.15
    ardy
    0.14
    ãģĮãģĬ
    0.14
    innie
    0.14
    rored
    0.14
    Act Density 0.176%

    No Known Activations