INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ideaal
    -0.08
    erral
    -0.08
     kijken
    -0.08
    teren
    -0.08
     obi
    -0.07
     dismant
    -0.07
     Siemens
    -0.07
     hassles
    -0.07
    -0.07
    .Uri
    -0.07
    POSITIVE LOGITS
     emotion
    0.12
     emotions
    0.11
     emociones
    0.11
     emoties
    0.10
     Emotion
    0.10
     sentiment
    0.09
     эмо
    0.09
     emoções
    0.09
    0.09
    Emotion
    0.09
    Act Density 0.014%

    No Known Activations