INDEX
    Explanations

    references to collaboration and community activities

    New Auto-Interp
    Negative Logits
    »↵
    -0.21
    «
    -0.17
    »↵↵
    -0.17
     «
    -0.17
    »:
    -0.16
    .»
    -0.16
    `↵
    -0.16
     âĢĮ
    -0.16
    »
    -0.16
    »,
    -0.15
    POSITIVE LOGITS
     ''
    0.44
    ''
    0.42
    :''
    0.37
    ``
    0.37
    ,''
    0.37
    .''
    0.37
    '',
    0.36
     ``
    0.36
     '',
    0.34
     ''↵
    0.34
    Act Density 0.101%

    No Known Activations