INDEX
    Explanations

    references to siblings and familial relationships, particularly brothers

    New Auto-Interp
    Negative Logits
    })));
    -0.77
     Gandalf
    -0.76
    UrlResolution
    -0.74
    )\}$
    -0.74
    apunov
    -0.72
     ECS
    -0.71
    isticated
    -0.70
     CLR
    -0.69
     virt
    -0.68
     Aitken
    -0.67
    POSITIVE LOGITS
     BROTHER
    1.28
     brother
    1.20
    brother
    1.19
     brothers
    1.17
     Brother
    1.17
     Broder
    1.14
    Brother
    1.14
     Brothers
    1.05
     Bro
    1.04
     sister
    1.01
    Act Density 0.066%

    No Known Activations