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

    Neuronpedia

    INDEX
    Explanations

    references to specific paragraphs within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific paragraphs and subsections within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.88
    ocker
    -0.79
    eus
    -0.75
     Robo
    -0.66
    ereo
    -0.65
     Tycoon
    -0.65
    ebus
    -0.64
    oppable
    -0.64
    ayne
    -0.63
    awaru
    -0.63
    POSITIVE LOGITS
    witz
    1.03
     paragraph
    0.99
     paragraphs
    0.96
    agraph
    0.92
    paragraph
    0.92
     subsections
    0.82
     subparagraph
    0.81
    acters
    0.79
     sections
    0.79
     subsection
    0.76
    Act Density 0.016%

    No Known Activations