INDEX
    Explanations

    references to geographical locations or political entities

    New Auto-Interp
    Negative Logits
    eting
    -0.18
    lyn
    -0.17
    ancock
    -0.14
    _md
    -0.14
    ogen
    -0.14
    çĤī
    -0.13
    esz
    -0.13
    448
    -0.13
    ActivityCreated
    -0.13
    teste
    -0.13
    POSITIVE LOGITS
    ypi
    0.16
    osexual
    0.14
    à¸IJ
    0.14
    alim
    0.14
    .GetText
    0.14
    :selected
    0.14
    elik
    0.14
    aight
    0.14
    Thrown
    0.13
    gba
    0.13
    Act Density 0.103%

    No Known Activations