INDEX
    Explanations

    references to Jewish identity and the experiences of Jewish people

    New Auto-Interp
    Negative Logits
    fak
    -0.15
    ropri
    -0.15
    æ»
    -0.14
     gameplay
    -0.14
     playable
    -0.14
    mere
    -0.13
    λιο
    -0.13
    ear
    -0.13
    ãĥ¼ãĥŃ
    -0.13
     repeatedly
    -0.13
    POSITIVE LOGITS
     fin
    0.20
     quit
    0.19
     essay
    0.18
     som
    0.18
     abandon
    0.17
     rent
    0.17
     fu
    0.17
    quit
    0.16
     tom
    0.16
    odb
    0.16
    Act Density 0.023%

    No Known Activations