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

    Neuronpedia

    INDEX
    Explanations

    tense markers and delimiters often used in legal or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     :\\
    -0.86
    ]\\
    -0.74
    ?\\
    -0.74
     
    -0.73
    .\\
    -0.73
     \$
    -0.71
    .”.
    -0.69
    \\
    -0.68
    -\\
    -0.67
    ).\\
    -0.66
    POSITIVE LOGITS
    <em>
    2.34
    <i>
    2.33
    <code>
    1.40
    《
    1.00
     /*
    1.00
     
    0.99
     `
    0.99
    /*
    0.98
     《
    0.89
    『
    0.84
    Act Density 0.784%

    No Known Activations