INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Reconnect
    -0.08
     Prü
    -0.08
     colspan
    -0.08
     phosphory
    -0.07
    ories
    -0.07
    ocin
    -0.07
     burada
    -0.07
     electroly
    -0.07
     crossover
    -0.07
    andır
    -0.07
    POSITIVE LOGITS
    0.11
     carving
    0.11
     machining
    0.10
     sculpture
    0.10
     sculptures
    0.10
     engraving
    0.10
     sculpt
    0.10
     masterpieces
    0.10
     нож
    0.09
     painstaking
    0.09
    Act Density 0.024%

    No Known Activations