INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     namely
    -0.08
     직접
    -0.08
    Lub
    -0.08
    Josh
    -0.08
     Lub
    -0.08
     Pedro
    -0.08
     Convenience
    -0.07
     convenience
    -0.07
    .partial
    -0.07
     Convention
    -0.07
    POSITIVE LOGITS
     эмо
    0.09
     melanch
    0.09
     emociones
    0.08
     sg
    0.08
     émotions
    0.08
     festive
    0.08
     emotionally
    0.08
     emotions
    0.08
     emocional
    0.08
     sombre
    0.08
    Act Density 0.003%

    No Known Activations