INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     incrível
    -0.08
    -0.08
     Paragu
    -0.08
    -0.07
    -0.07
     Powerful
    -0.07
    986
    -0.07
    .receiver
    -0.07
    )를
    -0.07
     directed
    -0.07
    POSITIVE LOGITS
     switches
    0.09
    Jump
    0.09
     switching
    0.08
    poz
    0.08
     jumps
    0.08
     والص
    0.08
    	switch
    0.08
    Switch
    0.08
     Jump
    0.07
     shout
    0.07
    Act Density 0.014%

    No Known Activations