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

    Neuronpedia

    INDEX
    Explanations

    sections or categories within a larger document

    oai_token-act-pair · gpt-3.5-turbo

    references to sections in a document or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Iv
    -0.79
    cia
    -0.79
    claimed
    -0.67
    Pri
    -0.67
    ILLE
    -0.65
    Grand
    -0.61
    ce
    -0.60
    inently
    -0.60
    aukee
    -0.59
    Fel
    -0.58
    POSITIVE LOGITS
    enium
    0.84
     sections
    0.82
    witz
    0.82
    lation
    0.78
    osaurs
    0.76
    owell
    0.73
     section
    0.73
    ttes
    0.72
     dumps
    0.71
    section
    0.71
    Act Density 0.011%

    No Known Activations