INDEX
    Explanations

    references to children's literature and associated themes

    New Auto-Interp
    Negative Logits
    beck
    -0.17
    atform
    -0.15
    uma
    -0.15
     вед
    -0.15
    åζ
    -0.15
     Haram
    -0.14
     mes
    -0.14
    esome
    -0.14
    esa
    -0.14
    anto
    -0.14
    POSITIVE LOGITS
     \@
    0.16
    çķĮ
    0.16
    issant
    0.15
    hti
    0.15
    InSection
    0.14
    NibName
    0.14
    -friendly
    0.14
    -gnu
    0.14
    ective
    0.14
    issing
    0.14
    Act Density 0.065%

    No Known Activations