INDEX
    Explanations

    occurrences of bracketed or quoted list items

    keys in data structures

    New Auto-Interp
    Negative Logits
    .},
    -0.53
    '});
    -0.49
    ."));
    -0.48
    =
    
    -0.48
    ]]:
    -0.48
    ')],
    -0.48
    ]();
    -0.47
    .}}
    -0.46
    -0.46
    -
    
    -0.45
    POSITIVE LOGITS
    ['
    1.81
    ["
    1.44
    ]['
    1.23
    ()['
    1.21
    ]["
    1.13
    [@"
    1.11
     ['
    1.08
    ')['
    1.03
    ']['
    1.03
    ['_
    1.00
    Act Density 0.007%

    No Known Activations