INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Ches
    -0.09
     incarnation
    -0.08
    sex
    -0.07
     bim
    -0.07
     göz
    -0.07
     Peter
    -0.07
     Dana
    -0.07
    CE
    -0.07
     Ener
    -0.07
     Mam
    -0.07
    POSITIVE LOGITS
     affairs
    0.08
    -town
    0.08
    work
    0.08
    yard
    0.08
    fuck
    0.08
     heroes
    0.08
    mate
    0.08
    setter
    0.07
    plots
    0.07
    folk
    0.07
    Act Density 0.025%

    No Known Activations