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

    Neuronpedia

    INDEX
    Explanations

    text related to regulations or structured documents such as paragraphs

    oai_token-act-pair · gpt-3.5-turbo

    references to specific paragraphs or sections within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.79
    awaru
    -0.71
    ocker
    -0.69
    ereo
    -0.68
    CV
    -0.68
    xon
    -0.67
    ayne
    -0.66
    ENSE
    -0.66
    eus
    -0.65
    asio
    -0.65
    POSITIVE LOGITS
    witz
    1.06
    acters
    0.87
    agraph
    0.86
    paragraph
    0.85
     paragraph
    0.83
    views
    0.77
     paragraphs
    0.74
     commenting
    0.74
     "$:/
    0.71
     subparagraph
    0.69
    Act Density 0.018%

    No Known Activations