INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    357
    -0.07
     jumps
    -0.07
    OVER
    -0.07
    Representative
    -0.07
    Sampling
    -0.07
    Counts
    -0.07
    Reli
    -0.07
     jump
    -0.07
     prendere
    -0.07
    Jump
    -0.07
    POSITIVE LOGITS
     giữa
    0.10
     паміж
    0.09
     Layout
    0.09
     pagitan
    0.08
    sett
    0.08
     між
    0.08
     acomod
    0.08
     wobei
    0.08
     boter
    0.08
     separados
    0.08
    Act Density 0.007%

    No Known Activations