INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     позвоноч
    -0.10
     кост
    -0.08
     expos
    -0.07
     функциони
    -0.07
    ogeneous
    -0.07
     Arbeiten
    -0.07
    -0.07
     Nazi
    -0.07
    ณฑ
    -0.07
    ====
    -0.07
    POSITIVE LOGITS
     emotions
    0.21
     feelings
    0.18
     эмо
    0.16
     emociones
    0.15
     sentimentos
    0.15
     emoções
    0.15
     sentimientos
    0.15
     emoties
    0.14
     gevoelens
    0.14
     émotions
    0.14
    Act Density 0.059%

    No Known Activations