INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     mourn
    -0.09
     flank
    -0.08
     paced
    -0.08
     Fest
    -0.08
     quake
    -0.08
     intensa
    -0.08
     locomotive
    -0.08
     frantic
    -0.08
     spa
    -0.07
     thirsty
    -0.07
    POSITIVE LOGITS
     Stav
    0.09
     adjusted
    0.09
    0.08
     goodness
    0.08
     pharmaceutical
    0.08
     term
    0.08
    Adjusted
    0.08
     adjustment
    0.08
    0.08
    Phrase
    0.08
    Act Density 0.056%

    No Known Activations