INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     figliu
    -0.77
     feroit
    -0.77
     étoit
    -0.76
     pouvoit
    -0.76
     quæ
    -0.75
     démission
    -0.74
     âgé
    -0.71
     passés
    -0.71
     colorés
    -0.71
     sortant
    -0.71
    POSITIVE LOGITS
     Audiodateien
    0.46
     esat
    0.36
     betweenstory
    0.34
    ...</
    0.32
     ​​
    0.31
     fucking
    0.29
     compi
    0.28
    Bronnen
    0.27
    ]")]
    0.27
     TextAppearance
    0.27
    Act Density 0.002%

    No Known Activations