INDEX
    Explanations

    mathematical symbols

    New Auto-Interp
    Negative Logits
     antibiotic
    -0.08
     Dale
    -0.08
    pton
    -0.08
     wards
    -0.08
     antibacterial
    -0.08
    Recipient
    -0.08
    God
    -0.08
    -0.07
    Metrics
    -0.07
     pamph
    -0.07
    POSITIVE LOGITS
     offset
    0.11
     OFFSET
    0.10
    OFFSET
    0.10
    offset
    0.10
     Offset
    0.10
    -offset
    0.09
     shift
    0.09
    _offset
    0.09
    	offset
    0.09
    _OFFSET
    0.09
    Act Density 0.030%

    No Known Activations