INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     학생들이
    0.51
     студен
    0.50
    학생
    0.48
     студентов
    0.47
    0.46
     학생
    0.46
    պ
    0.45
    Students
    0.44
     Students
    0.44
     छात्रों
    0.44
    POSITIVE LOGITS
     baby
    2.72
     infant
    2.63
     Baby
    2.45
    Baby
    2.44
    baby
    2.41
     babies
    2.38
     infants
    2.36
    婴儿
    2.34
     Infant
    2.31
     Babies
    2.23
    Act Density 0.081%

    No Known Activations