INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     being
    -1.95
    being
    -1.72
    Being
    -1.50
     Being
    -1.44
     BEING
    -1.41
     étant
    -1.35
     having
    -1.16
     essendo
    -1.13
     sendo
    -1.12
     fiind
    -1.09
    POSITIVE LOGITS
     woken
    0.73
     able
    0.66
    "]="
    0.66
     bullied
    0.63
    ]--;
    0.63
    IUrlHelper
    0.63
     dragged
    0.61
     eaten
    0.60
     touched
    0.60
    ]!='
    0.59
    Act Density 0.048%

    No Known Activations