INDEX
    Explanations

    file extension names

    references to web-related terms and various fictional media

    New Auto-Interp
    Negative Logits
    .).
    -1.45
    .),
    -1.16
    .):
    -1.08
    ?).
    -1.04
     ).
    -1.02
    .)
    -1.01
    .]
    -0.99
     .)
    -0.95
     });
    -0.91
     ].
    -0.89
    POSITIVE LOGITS
    "
    2.23
    "-
    1.76
    "'
    1.71
    "?
    1.63
    %"
    1.57
    "(
    1.54
    "...
    1.51
    "[
    1.47
    ''
    1.46
    "—
    1.44
    Act Density 0.563%

    No Known Activations