INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     காத
    -0.09
     earning
    -0.09
    beg
    -0.09
     gloves
    -0.08
     vacances
    -0.08
     earrings
    -0.08
     Lernen
    -0.08
     impar
    -0.08
     muñ
    -0.08
     iq
    -0.07
    POSITIVE LOGITS
    国内
    0.18
     domest
    0.16
     국내
    0.16
     domestic
    0.15
     国内
    0.15
     Domestic
    0.13
     domést
    0.13
     내부
    0.13
    Domestic
    0.13
    内部
    0.13
    Act Density 0.100%

    No Known Activations