INDEX
    Explanations

    terms related to child and sexual abuse, as well as corruption

    New Auto-Interp
    Negative Logits
    ffen
    -0.15
    armor
    -0.15
    ntl
    -0.14
    ENTER
    -0.14
    rum
    -0.14
    ëıħ
    -0.14
     Dependency
    -0.14
    æģ©
    -0.13
    EDIUM
    -0.13
    ystore
    -0.13
    POSITIVE LOGITS
    iveness
    0.21
    aylight
    0.16
    stin
    0.16
    -chevron
    0.15
     Hend
    0.15
    erland
    0.15
     "...
    0.14
    stown
    0.14
    /loose
    0.14
    aken
    0.14
    Act Density 0.061%

    No Known Activations