INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
     practitioner
    -0.08
     practitioners
    -0.08
    -0.07
    .directory
    -0.07
    observe
    -0.07
     jack
    -0.07
     conce
    -0.07
    -0.07
     unnatural
    -0.07
    POSITIVE LOGITS
     Maur
    0.09
    Sen
    0.07
     hill
    0.07
     sen
    0.07
     Richards
    0.07
     Sen
    0.07
     spacecraft
    0.07
    ін
    0.07
     Pagan
    0.07
     Scam
    0.07
    Act Density 0.003%

    No Known Activations