INDEX
    Explanations

    references to boys or male individuals

    New Auto-Interp
    Negative Logits
     objective
    -1.40
    objective
    -1.24
     Objective
    -1.23
    Objective
    -1.09
     OBJECTIVE
    -1.07
     objectives
    -0.91
    OBJECTIVE
    -0.89
     Objectives
    -0.81
    objectives
    -0.79
     objectively
    -0.77
    POSITIVE LOGITS
    Boy
    2.58
     Boy
    2.56
     boy
    2.56
    boy
    2.31
     BOY
    2.28
    BOY
    2.13
    boys
    1.72
     boys
    1.66
    Boys
    1.66
     Boys
    1.65
    Act Density 0.033%

    No Known Activations