INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     usuario
    -0.07
     hacker
    -0.07
    -0.06
     sin
    -0.06
     كبيرة
    -0.06
    antaged
    -0.06
     ус
    -0.06
    vert
    -0.06
     waiver
    -0.06
    rottle
    -0.06
    POSITIVE LOGITS
    (**
    0.07
    0.07
     lineHeight
    0.06
                   
    0.06
     strokeWidth
    0.06
    wik
    0.06
     investigate
    0.06
    .wik
    0.06
    hy
    0.06
    .Details
    0.06
    Act Density 0.000%

    No Known Activations