INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    igo
    -0.85
     Parenthood
    -0.84
    umo
    -0.75
    atell
    -0.73
    ickr
    -0.71
     Rockies
    -0.68
    ername
    -0.67
    iator
    -0.66
     Popular
    -0.66
    arent
    -0.66
    POSITIVE LOGITS
    awk
    0.81
    tml
    0.80
    doms
    0.78
    awks
    0.73
    stick
    0.72
    sin
    0.72
    hovah
    0.71
    ttp
    0.70
    µ
    0.67
    hawks
    0.66
    Act Density 0.051%

    No Known Activations