INDEX
    Explanations

    references to familial relationships, particularly involving siblings

    New Auto-Interp
    Negative Logits
    })));
    -0.91
    isticated
    -0.81
    })*/
    -0.79
     glan
    -0.78
     CLR
    -0.74
     ALC
    -0.73
    %]
    -0.72
    ']):
    -0.72
    "]}
    -0.72
    enment
    -0.71
    POSITIVE LOGITS
     brother
    1.77
     BROTHER
    1.71
     brothers
    1.69
    brother
    1.67
     sister
    1.62
    Brother
    1.57
     Brother
    1.55
     Sister
    1.47
    brothers
    1.46
     sisters
    1.45
    Act Density 0.045%

    No Known Activations