INDEX
    Explanations

    proper nouns related to people

    New Auto-Interp
    Negative Logits
    anooga
    -0.91
    unct
    -0.85
    ulates
    -0.84
    unal
    -0.82
    ornia
    -0.81
    ulate
    -0.81
    kered
    -0.80
    pload
    -0.80
    ixed
    -0.79
    awaru
    -0.78
    POSITIVE LOGITS
     Allen
    1.16
     Dull
    0.96
     Gins
    0.93
     Williamson
    0.83
     Lane
    0.81
    more
    0.81
     Dixon
    0.80
    verson
    0.77
    Allen
    0.77
     Robinson
    0.77
    Act Density 0.006%

    No Known Activations