INDEX
    Explanations

    references to the body and its attributes

    New Auto-Interp
    Negative Logits
    <bos>
    -2.65
     rehabilitate
    -0.81
     germinate
    -0.70
    -0.66
     defray
    -0.62
     innovate
    -0.62
    /**
    -0.62
     trod
    -0.62
     nursed
    -0.61
     ratify
    -0.61
    POSITIVE LOGITS
     body
    1.20
     Body
    1.17
    body
    1.13
     BODY
    1.11
    Body
    1.10
     lele
    1.07
    BODY
    1.03
    getBody
    1.00
     jawa
    0.95
     jaya
    0.94
    Act Density 0.068%

    No Known Activations