INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Uri
    -0.08
     Variety
    -0.08
    Kit
    -0.08
     Pit
    -0.07
     Eli
    -0.07
    Emoji
    -0.07
     PIT
    -0.07
     Woj
    -0.07
     Api
    -0.07
     itemId
    -0.07
    POSITIVE LOGITS
     descent
    0.08
     ascend
    0.08
     descended
    0.08
    ц
    0.08
     descendants
    0.08
    zd
    0.08
     down
    0.08
     ascending
    0.08
     descend
    0.07
     descendant
    0.07
    Act Density 0.017%

    No Known Activations