INDEX
    Explanations

    references to young males and females in various contexts

    New Auto-Interp
    Negative Logits
    seamnă
    -0.64
    ÑO
    -0.59
     Eocene
    -0.54
     prochains
    -0.54
     tuturor
    -0.54
     Darío
    -0.53
    isier
    -0.52
    anet
    -0.52
    siger
    -0.52
    crites
    -0.52
    POSITIVE LOGITS
     who
    0.94
     woman
    0.92
     gentleman
    0.83
     guy
    0.82
     person
    0.80
     man
    0.78
     bloke
    0.74
     TestBed
    0.73
    RenderAtEndOf
    0.72
     himself
    0.67
    Act Density 0.281%

    No Known Activations