INDEX
    Explanations

    words related to people, specifically referencing males

    references to male individuals or groups in a context

    New Auto-Interp
    Negative Logits
    ories
    -0.79
     Hobby
    -0.74
    isson
    -0.70
     Hacker
    -0.68
     Lent
    -0.67
     copyright
    -0.66
    cop
    -0.66
    cephal
    -0.65
     Feminist
    -0.65
    cens
    -0.64
    POSITIVE LOGITS
     drafted
    0.80
     scouts
    0.77
     underneath
    0.74
     scout
    0.71
     starters
    0.71
     sacrificed
    0.70
     swaps
    0.70
    bilt
    0.70
     acquisitions
    0.69
     signings
    0.69
    Act Density 0.075%

    No Known Activations