INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Gui
    -0.07
    _smooth
    -0.07
    сто
    -0.07
     dataset
    -0.07
     apache
    -0.07
    gc
    -0.07
     scop
    -0.07
    Btn
    -0.07
     soup
    -0.06
    _pa
    -0.06
    POSITIVE LOGITS
     Pir
    0.07
     hải
    0.07
     Candid
    0.07
     bulund
    0.07
     בעלי
    0.07
     Wohn
    0.07
     stationed
    0.07
     referenced
    0.07
     בעל
    0.07
     chim
    0.07
    Act Density 0.182%

    No Known Activations