INDEX
    Explanations

    words related to the color purple

    references to the term "Puritan."

    New Auto-Interp
    Negative Logits
    enegger
    -0.86
    ORGE
    -0.85
    worthiness
    -0.83
     removable
    -0.69
    doms
    -0.69
    è¦ļéĨĴ
    -0.68
    apper
    -0.67
    schild
    -0.65
    ews
    -0.65
    ographies
    -0.64
    POSITIVE LOGITS
    POSE
    1.04
    pose
    1.03
    poses
    1.03
    ple
    0.98
    ported
    0.97
    usha
    0.89
    pee
    0.79
    izon
    0.79
    pure
    0.78
    zees
    0.77
    Act Density 0.022%

    No Known Activations