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

    Neuronpedia

    INDEX
    Explanations

    references in academic texts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     thrott
    -0.62
    estate
    -0.61
    vered
    -0.61
     chops
    -0.61
    arers
    -0.60
    roph
    -0.59
    split
    -0.59
    orate
    -0.59
    ties
    -0.58
    Ń·
    -0.58
    POSITIVE LOGITS
    pmwiki
    0.96
    ibliography
    0.95
    Sources
    0.90
    BOOK
    0.87
    âĨij
    0.86
    agascar
    0.85
    sites
    0.81
     Encyclopedia
    0.78
    Books
    0.77
     Sources
    0.76
    Act Density 16.297%

    No Known Activations