INDEX
    Explanations

    names of public figures associated with controversial issues

    New Auto-Interp
    Negative Logits
    oya
    -0.16
    pes
    -0.16
    uida
    -0.14
     sometime
    -0.14
    inen
    -0.14
    å®ļ
    -0.14
    oxic
    -0.14
     these
    -0.14
    rink
    -0.13
    ien
    -0.13
    POSITIVE LOGITS
    lod
    0.16
    çĦ¶èĢĮ
    0.15
    abor
    0.15
     Lodge
    0.14
    lol
    0.14
    $MESS
    0.14
     lodge
    0.14
    naÄįenÃŃ
    0.14
    ']=="
    0.13
    )const
    0.13
    Act Density 0.000%

    No Known Activations