INDEX
    Explanations

    references to Jewish culture, specifically related to traditional practices and historical contexts

    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.75
     Jefus
    -0.74
    -0.68
     vns
    -0.67
     Theſe
    -0.67
     Aene
    -0.63
     Thun
    -0.63
     sánh
    -0.63
     itſelf
    -0.62
     Duy
    -0.62
    POSITIVE LOGITS
     Jewish
    1.16
     Israeli
    1.14
     Israel
    1.12
     Aviv
    1.09
     Jews
    1.03
    Israel
    1.01
    Jewish
    0.99
    Israeli
    0.96
     Israël
    0.96
    anyahu
    0.94
    Act Density 0.297%

    No Known Activations