INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    elem
    -0.08
    ury
    -0.08
     Oce
    -0.08
     cro
    -0.08
    -0.08
     cabinet
    -0.08
     termite
    -0.08
     lep
    -0.07
     Vitt
    -0.07
     lumen
    -0.07
    POSITIVE LOGITS
    omial
    0.08
     каж
    0.08
     Cull
    0.08
    -down
    0.07
     gloss
    0.07
    0.07
    Around
    0.07
    0.07
    lify
    0.07
    0.07
    Act Density 0.007%

    No Known Activations