INDEX
    Explanations

    terms related to political criticism and ideological conflict

    New Auto-Interp
    Negative Logits
     Blonde
    -0.16
    ulong
    -0.14
    .DataTable
    -0.14
    اØ
    -0.14
    pec
    -0.14
    :selected
    -0.14
    less
    -0.14
     Conspiracy
    -0.13
    fixtures
    -0.13
    paren
    -0.13
    POSITIVE LOGITS
    asics
    0.15
    äs
    0.15
    emony
    0.14
    oston
    0.14
    ektor
    0.14
     Pied
    0.14
    ãĥ
    0.14
     æį
    0.14
    AGO
    0.14
     filt
    0.14
    Act Density 0.598%

    No Known Activations