INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     skirts
    0.41
     rows
    0.40
     lamps
    0.40
     units
    0.38
     sprays
    0.38
     dolls
    0.38
     soluble
    0.38
     chrome
    0.37
     adulter
    0.37
     primitives
    0.37
    POSITIVE LOGITS
    出身
    0.77
     geboren
    0.70
     berasal
    0.68
     pochod
    0.65
     hailing
    0.64
     upbringing
    0.63
     hometown
    0.62
     původ
    0.62
     born
    0.59
     immigrant
    0.59
    Act Density 0.037%

    No Known Activations