INDEX
    Explanations

    describing physical attributes

    New Auto-Interp
    Negative Logits
    0.54
    Categ
    0.52
    Damage
    0.51
    क्ष्य
    0.47
    なく
    0.47
    0.47
     layoff
    0.46
    ूरिया
    0.46
    ना
    0.46
    0.46
    POSITIVE LOGITS
     conquered
    0.41
     comercio
    0.40
     conquer
    0.39
    han
    0.39
     authoritarian
    0.39
     supremo
    0.39
     dirigeants
    0.38
     encargado
    0.38
     totalitarian
    0.37
     متنوع
    0.37
    Act Density 0.002%

    No Known Activations