INDEX
    Explanations

    antisemitic content related to Jewish people, particularly content that mentions Jews in a negative or conspiratorial context.

    New Auto-Interp
    Negative Logits
     PEM
    -0.07
    -0.06
     predomin
    -0.06
     HID
    -0.06
     LinearGradient
    -0.06
    dığ
    -0.06
     Sly
    -0.06
    (Unit
    -0.06
     долж
    -0.06
    =url
    -0.06
    POSITIVE LOGITS
     apis
    0.06
     Spir
    0.06
    onClick
    0.06
    .Cells
    0.06
    стория
    0.06
    _Set
    0.06
     تحص
    0.06
     routing
    0.06
    μοί
    0.06
     yc
    0.06
    Act Density 0.010%

    No Known Activations