INDEX
    Explanations

    symbols, numbers, and the presence of copyright indicators

    New Auto-Interp
    Negative Logits
    opensource
    -0.14
    aleigh
    -0.14
    ãĥªãĤ¢
    -0.14
    oren
    -0.13
     Knights
    -0.13
     Gent
    -0.13
    oner
    -0.13
    ocs
    -0.13
     end
    -0.13
     fact
    -0.13
    POSITIVE LOGITS
    Copyright
    0.27
     Copyright
    0.27
    opyright
    0.24
     copyright
    0.22
    copyright
    0.22
    202
    0.20
     COPYRIGHT
    0.19
    	Copyright
    0.19
    tml
    0.18
    kowski
    0.17
    Act Density 0.005%

    No Known Activations