INDEX
    Explanations

    documentation/annotation markers

    New Auto-Interp
    Negative Logits
    0
    0.40
     reform
    0.39
     
    0.38
     harm
    0.37
     expansion
    0.37
     health
    0.37
     row
    0.36
     softly
    0.36
    9
    0.36
     grow
    0.36
    POSITIVE LOGITS
    ----------------
    0.79
     NOTE
    0.61
    ================
    0.60
    ****************
    0.57
     ---------------
    0.55
    ---------------
    0.54
     Certaines
    0.54
     Viele
    0.52
     Please
    0.51
     WARNING
    0.51
    Act Density 0.004%

    No Known Activations