INDEX
    Explanations

    mentions of historical figures, specifically focusing on Theodore Roosevelt

    references to historical figures, particularly Theodore Roosevelt

    New Auto-Interp
    Negative Logits
    Loading
    -0.69
    Buzz
    -0.68
    OIL
    -0.68
    birth
    -0.65
    gans
    -0.64
    places
    -0.64
    points
    -0.63
    shapeshifter
    -0.62
    ebook
    -0.61
    respect
    -0.61
    POSITIVE LOGITS
     Roosevelt
    1.17
     Theodore
    0.97
    sonian
    0.86
    itus
    0.83
     Herz
    0.81
    sson
    0.80
    eteenth
    0.79
    \\\\\\\\
    0.77
    ufact
    0.75
     Sturgeon
    0.74
    Act Density 0.011%

    No Known Activations