INDEX
    Explanations

    mentions of specific names, likely focusing on names that start with "Mc"

    proper nouns, particularly names

    New Auto-Interp
    Negative Logits
     Gemini
    -0.95
     Mercury
    -0.82
     Galileo
    -0.72
     Prometheus
    -0.72
     Guilty
    -0.71
     Europa
    -0.71
     CBI
    -0.67
     Apollo
    -0.64
    âķIJâķIJ
    -0.63
    é¾įå
    -0.63
    POSITIVE LOGITS
    intosh
    1.01
    ath
    1.00
    arty
    1.00
    hews
    0.96
     McGr
    0.90
    etz
    0.89
    aths
    0.87
    iless
    0.84
    hew
    0.82
    reath
    0.82
    Act Density 0.012%

    No Known Activations