INDEX
    Explanations

    multiple languages

    New Auto-Interp
    Negative Logits
    iei
    -0.10
    intel
    -0.09
    ì
    -0.08
     Mani
    -0.08
    mongo
    -0.07
     Madeira
    -0.07
     Gio
    -0.07
     Mick
    -0.07
     Dauer
    -0.07
     Justice
    -0.07
    POSITIVE LOGITS
     fotos
    0.07
     excitation
    0.07
     куз
    0.07
     repell
    0.07
     transmit
    0.07
     excited
    0.07
     perguntar
    0.07
     parç
    0.07
     needed
    0.07
     gostaria
    0.07
    Act Density 0.103%

    No Known Activations