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

    Neuronpedia

    INDEX
    Explanations

    instances of code snippets and formatting within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.77
    .";
    -0.69
    Discus
    -0.66
    portlet
    -0.64
     dias
    -0.62
     ares
    -0.61
     Jahr
    -0.61
     QName
    -0.59
     days
    -0.58
     المتحدة
    -0.57
    POSITIVE LOGITS
    <code>
    1.84
    <em>
    1.10
    <i>
    1.10
    </code>
    1.04
    ｢
    1.03
    <u>
    1.02
    <h6>
    1.02
     `
    1.00
    __(/*!
    1.00
    <s>
    0.99
    Act Density 0.187%

    No Known Activations