INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     opsi
    1.19
     riguardo
    1.02
     ogni
    0.99
     analisi
    0.96
     tzw
    0.94
     qualche
    0.93
     czyli
    0.93
     quanto
    0.92
     către
    0.90
     Änderungen
    0.90
    POSITIVE LOGITS
     women
    1.07
     keepsake
    0.98
     people
    0.93
     dresser
    0.93
     courtyard
    0.89
     woman
    0.84
     ponytail
    0.84
     wearer
    0.84
     handyman
    0.82
     voters
    0.82
    Act Density 0.088%

    No Known Activations