INDEX
    Explanations

    references to religious authority and doctrine

    New Auto-Interp
    Negative Logits
    ignon
    -0.20
    Interop
    -0.16
    peak
    -0.15
     Peak
    -0.15
    ARGIN
    -0.14
    Peak
    -0.14
    ãĥĶãĥ¼
    -0.14
    ipse
    -0.14
    aroo
    -0.14
    chap
    -0.14
    POSITIVE LOGITS
    untime
    0.15
    ixmap
    0.15
    ä¾į
    0.15
     Lakes
    0.14
    ORLD
    0.14
    ulls
    0.14
    ovies
    0.14
     reins
    0.14
    _ak
    0.14
    ì¹
    0.13
    Act Density 0.069%

    No Known Activations