INDEX
    Explanations

    dates in the format "Month Day" such as "May 8"

    dates formatted as "May [day]" in the text

    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.71
    pn
    -0.67
     CODE
    -0.66
    */(
    -0.64
     Rage
    -0.63
     tray
    -0.63
     Scourge
    -0.61
    swick
    -0.61
     pree
    -0.59
    estern
    -0.59
    POSITIVE LOGITS
    nard
    1.40
    flower
    1.30
    onna
    1.21
    fair
    1.20
    weather
    1.16
    oral
    1.16
    hew
    1.11
    umi
    0.94
    bach
    0.93
    pole
    0.92
    Act Density 0.032%

    No Known Activations