INDEX
    Explanations

    references to Jewish people and Israel, often in the context of conspiracy and anti-Zionism

    Israel, Jews, antisemitism

    New Auto-Interp
    Negative Logits
    nestjs
    -0.28
     ser
    -0.25
    [
    -0.25
     pocas
    -0.24
     dàng
    -0.23
     golden
    -0.23
    Product
    -0.23
     tö
    -0.22
    Change
    -0.21
     hos
    -0.21
    POSITIVE LOGITS
     MainAxisSize
    0.87
     NSCoder
    0.76
    astify
    0.75
    AnchorStyles
    0.75
     synag
    0.74
    ロウィン
    0.73
    anyahu
    0.72
     zoude
    0.71
     SwitchCompat
    0.69
    Hauptartikel
    0.69
    Act Density 0.142%

    No Known Activations