INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     نش
    -0.07
    Answer
    -0.06
     Receive
    -0.06
    girl
    -0.06
     disrespectful
    -0.06
    Swipe
    -0.06
    -hover
    -0.06
     Beet
    -0.06
    -prop
    -0.06
    bcrypt
    -0.06
    POSITIVE LOGITS
    FDA
    0.07
    _workflow
    0.07
    icia
    0.07
    rising
    0.07
    0.07
     Etsy
    0.06
     FDA
    0.06
     recipes
    0.06
     QVBoxLayout
    0.06
    loud
    0.06
    Act Density 0.007%

    No Known Activations