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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.82
     and
    -0.80
     -
    -0.69
    -
    -0.67
     
    -0.67
     &
    -0.63
    .
    -0.62
    /
    -0.61
     –
    -0.59
    com
    -0.57
    POSITIVE LOGITS
    ".
    1.30
    ]";
    1.23
    .";
    1.17
    ")));
    1.16
    %";
    1.16
    .",
    1.15
    "]));
    1.10
    ),"
    1.10
    ],"
    1.09
    "]:
    1.07
    Act Density 0.755%

    No Known Activations