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

    Neuronpedia

    INDEX
    Explanations

    elements related to copyright, citations, and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '],
    -0.99
    '},
    -0.96
    `,
    -0.91
    ".
    -0.89
    __':
    -0.89
    %");
    -0.85
    '),
    -0.84
    `;
    -0.84
     ';
    -0.84
    "],
    -0.82
    POSITIVE LOGITS
    ↵↵↵
    0.77
    ↵↵
    0.73
    !!!
    0.72
    ↵↵↵↵
    0.71
    !
    0.69
    !!
    0.69
    !!!!
    0.65
    ↵
    0.62
    ↵↵↵↵↵
    0.61
    ↵↵↵↵↵↵
    0.59
    Act Density 0.449%

    No Known Activations