INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    bid
    -0.08
     slept
    -0.08
    -0.08
     losing
    -0.07
     slik
    -0.07
    -0.07
    -0.07
    ilian
    -0.07
     Herm
    -0.07
     пу
    -0.07
    POSITIVE LOGITS
    worthy
    0.08
    -worthy
    0.08
    kinson
    0.08
    Hair
    0.08
     chore
    0.08
     Geoffrey
    0.08
     cabe
    0.08
     bara
    0.08
     Kats
    0.08
     FAVOR
    0.08
    Act Density 0.004%

    No Known Activations