INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Various
    0.49
    various
    0.48
    Various
    0.47
     различни
    0.44
     المختلفة
    0.43
     Different
    0.42
     various
    0.42
     različ
    0.40
     forskellige
    0.40
     각종
    0.39
    POSITIVE LOGITS
     halves
    0.86
     sides
    0.84
     sexes
    0.83
     genders
    0.69
     parties
    0.62
     lados
    0.61
     sets
    0.60
     पक्षों
    0.59
     hemispheres
    0.56
     extremes
    0.54
    Act Density 0.036%

    No Known Activations