INDEX
    Explanations

    references to emotions and emotional experiences

    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.99
     nahilalakip
    -0.99
     للمعارف
    -0.98
    ſſung
    -0.91
     AssemblyCompany
    -0.89
    <pad>
    -0.88
    <unused79>
    -0.88
    <unused23>
    -0.88
    [@BOS@]
    -0.88
    <unused3>
    -0.88
    POSITIVE LOGITS
     emotions
    0.80
     feelings
    0.78
     emotion
    0.60
    emotions
    0.56
     emociones
    0.55
     эмоции
    0.54
    Emotions
    0.53
     Emotions
    0.53
     emotional
    0.51
     Feelings
    0.49
    Act Density 0.042%

    No Known Activations