Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the presence of document structure or formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.79
    _
    -0.78
    -
    -0.77
    /
    -0.63
    (
    -0.59
    ma
    -0.58
    us
    -0.58
    .
    -0.58
    ...
    -0.56
    ;
    -0.56
    POSITIVE LOGITS
    "):
    1.29
    )";
    1.19
     ')
    1.18
    )");
    1.18
    '))
    1.17
    "])
    1.17
    "]);
    1.15
    ")));
    1.15
    ']))
    1.11
     The
    1.09
    Act Density 0.317%

    No Known Activations