INDEX
    Explanations

    Image dimensions

    New Auto-Interp
    Negative Logits
    uls
    -0.08
     satisfait
    -0.08
    -0.08
     nuisance
    -0.08
    xes
    -0.08
    pares
    -0.08
    -0.08
     بابت
    -0.08
    HT
    -0.08
     Orwell
    -0.08
    POSITIVE LOGITS
     taller
    0.08
     vertical
    0.08
     guidance
    0.08
    vertical
    0.07
     вертик
    0.07
     hanging
    0.07
     act
    0.07
    ג
    0.07
     spiritual
    0.07
     Guidance
    0.07
    Act Density 0.020%

    No Known Activations