INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
    -0.08
     Perf
    -0.07
    actoring
    -0.07
    anted
    -0.07
    prt
    -0.07
     Confirmation
    -0.07
    594
    -0.07
    /conf
    -0.07
    Ba
    -0.07
    POSITIVE LOGITS
     Hardy
    0.09
    -Friday
    0.08
    weekday
    0.08
     Lisa
    0.08
     Leib
    0.08
    0.08
     Dorm
    0.08
    DAY
    0.07
     TG
    0.07
    week
    0.07
    Act Density 0.008%

    No Known Activations