INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Jei
    -0.11
     Pode
    -0.10
     Puede
    -0.10
     Cuando
    -0.10
     Sos
    -0.10
     Ieu
    -0.10
     Jeg
    -0.10
     Existem
    -0.10
     Hierbij
    -0.10
     Não
    -0.10
    POSITIVE LOGITS
     beneidenswert
    0.17
     männer
    0.15
     beneid
    0.13
     frauen
    0.13
     prü
    0.13
     kaffe
    0.12
     titel
    0.12
     risiko
    0.11
     kandidaten
    0.11
     rabatt
    0.11
    Act Density 0.015%

    No Known Activations