INDEX
    Explanations

    phrases related to historical figures, specifically those related to Theodore and Franklin Roosevelt

    references to Roosevelt, both Theodore and Franklin

    New Auto-Interp
    Negative Logits
    ateurs
    -0.76
    agen
    -0.75
    ellar
    -0.74
    leon
    -0.72
    ifier
    -0.70
    rar
    -0.69
    oreal
    -0.69
    osphere
    -0.68
    phabet
    -0.68
    ifer
    -0.67
    POSITIVE LOGITS
     Roosevelt
    1.28
    hower
    0.85
     Institution
    0.79
    enthal
    0.78
     Oaks
    0.77
     Geh
    0.75
    velt
    0.74
    dinand
    0.73
     Eisenhower
    0.72
     Doodle
    0.71
    Act Density 0.055%

    No Known Activations