INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     aeroporto
    -0.08
     operativo
    -0.08
     avion
    -0.08
     Fabio
    -0.08
     Avi
    -0.08
     labi
    -0.08
    ودي
    -0.08
     formando
    -0.07
     comunque
    -0.07
    -0.07
    POSITIVE LOGITS
    .swift
    0.07
    STE
    0.07
    zeug
    0.07
     '{
    0.07
    nte
    0.07
    .bot
    0.07
    .dm
    0.07
    945
    0.07
    =current
    0.07
    -te
    0.07
    Act Density 0.002%

    No Known Activations