INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     star
    -0.46
     puck
    -0.44
    ster
    -0.44
     Grey
    -0.43
     tit
    -0.43
     asset
    -0.43
     compressed
    -0.42
     Star
    -0.42
     Zar
    -0.42
     Cain
    -0.42
    POSITIVE LOGITS
     Normdatei
    0.69
     normaux
    0.66
    +#+#
    0.66
     inoxydable
    0.63
     automatiques
    0.62
     âmes
    0.60
     inappropriés
    0.59
     sécurisé
    0.59
     positifs
    0.59
     quelcon
    0.58
    Act Density 0.026%

    No Known Activations