INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Brown
    -0.07
    บก
    -0.07
     Mama
    -0.06
     gọi
    -0.06
     Rural
    -0.06
    Artist
    -0.06
    ität
    -0.06
     Alibaba
    -0.06
    -Israel
    -0.06
    		   
    -0.06
    POSITIVE LOGITS
     إذا
    0.07
    ้าส
    0.06
    APPLE
    0.06
    >Welcome
    0.06
     interracial
    0.06
     mData
    0.06
    _spi
    0.06
    --)↵
    0.06
    :I
    0.06
     нес
    0.06
    Act Density 0.004%

    No Known Activations