INDEX
    Explanations

    mentions of specific female names

    New Auto-Interp
    Negative Logits
    shit
    -0.79
    cffff
    -0.75
    asper
    -0.72
    ozy
    -0.71
    pelled
    -0.71
    pec
    -0.69
    yg
    -0.69
    doors
    -0.69
    sed
    -0.69
    */(
    -0.68
    POSITIVE LOGITS
     Louise
    1.12
     Marie
    1.08
     Thatcher
    1.06
     Anne
    1.06
     DeVos
    1.05
     Mae
    1.03
     Jane
    1.02
    Marie
    1.01
     herself
    1.00
     Margaret
    0.98
    Act Density 0.064%

    No Known Activations