INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.62
     sağlay
    -0.48
     muhte
    -0.44
     المعيارى
    -0.42
     Combined
    -0.41
     nového
    -0.41
    Likely
    -0.41
    nieuw
    -0.41
     contenir
    -0.41
    GetAxis
    -0.40
    POSITIVE LOGITS
    shirt
    1.41
    Shirt
    1.21
    shirts
    1.21
     tshirt
    1.04
    tshirt
    1.02
    Shirts
    0.93
    hirt
    0.86
     shirt
    0.84
     футболка
    0.80
     camiseta
    0.80
    Act Density 0.002%

    No Known Activations