INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     pouvoirs
    -0.65
     autorités
    -0.59
     consommateurs
    -0.59
     déclarations
    -0.57
     ouvriers
    -0.56
     négociations
    -0.56
    vician
    -0.55
     prochaines
    -0.55
     producteurs
    -0.54
     investissements
    -0.54
    POSITIVE LOGITS
    tags
    0.80
    rooms
    0.75
    httphttps
    0.73
    Gön
    0.72
    hips
    0.72
    bands
    0.71
    sheets
    0.70
    rings
    0.69
    masks
    0.69
    books
    0.69
    Act Density 0.066%

    No Known Activations