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

    Neuronpedia

    INDEX
    Explanations

    structural or formatting elements in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </em>
    -2.34
    </i>
    -2.02
    </blockquote>
    -1.81
    <unused63>
    -1.74
    </h6>
    -1.72
    </code>
    -1.71
    <unused61>
    -1.67
    </s>
    -1.64
    <unused60>
    -1.64
    <unused62>
    -1.59
    POSITIVE LOGITS
    <h2>
    0.55
    NOPQRST
    0.54
    ，《
    0.50
    LookAnd
    0.50
    cshtml
    0.49
    、“
    0.49
     تكبرها
    0.47
     createState
    0.47
    ={
    0.47
    ，“
    0.46
    Act Density 0.061%

    No Known Activations