INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     یہودی
    0.58
     یہودیوں
    0.55
     евре
    0.50
     Jewish
    0.49
     اليه
    0.49
     judíos
    0.49
     Jews
    0.48
     synagogue
    0.47
     اسرائیلی
    0.45
    Jewish
    0.45
    POSITIVE LOGITS
     running
    0.45
     fitness
    0.43
     pob
    0.43
     Air
    0.43
     Golden
    0.43
     peças
    0.43
     bagged
    0.42
     Imran
    0.42
     slimming
    0.42
     Fernanda
    0.42
    Act Density 0.014%

    No Known Activations