INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.77
     betweenstory
    -0.64
     neutral
    -0.59
     épreuves
    -0.59
     écout
    -0.58
     isComment
    -0.56
    ]")]
    -0.55
    fois
    -0.54
    nelt
    -0.53
    InSection
    -0.53
    POSITIVE LOGITS
     mer
    0.57
     Coven
    0.56
     indignation
    0.54
    Javadoc
    0.54
     providence
    0.53
     pastime
    0.53
    ingar
    0.52
    ovan
    0.52
     propTypes
    0.52
     digestion
    0.51
    Act Density 0.202%

    No Known Activations