INDEX
    Explanations

    you'll do/find/need/want

    New Auto-Interp
    Negative Logits
     bothers
    0.46
     (){
    0.45
     alleles
    0.45
     sorgt
    0.42
    なのですが
    0.42
     muestran
    0.41
     rigging
    0.40
     misdemean
    0.40
     ligation
    0.40
     terminates
    0.39
    POSITIVE LOGITS
     yourself
    0.80
     pouvez
    0.73
     Yourself
    0.66
     devrez
    0.65
     need
    0.64
    하실
    0.63
     notice
    0.59
     будете
    0.58
    yourself
    0.57
     trouverez
    0.57
    Act Density 0.004%

    No Known Activations