INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    I
    0.48
    Σ
    0.45
    ီး
    0.44
    footnotesize
    0.42
     corresponded
    0.42
    ዘጋ
    0.41
     mayonnaise
    0.41
    ék
    0.41
    Т
    0.40
    Х
    0.40
    POSITIVE LOGITS
     نفرت
    0.46
    AGMENT
    0.45
     endometri
    0.45
     dien
    0.44
     शीट
    0.44
     atividades
    0.44
     कमी
    0.43
    పురం
    0.43
     الشباب
    0.42
    jenigen
    0.42
    Act Density 0.005%

    No Known Activations