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

    Neuronpedia

    INDEX
    Explanations

    news-related words such as "news" and "newsletter"

    oai_token-act-pair · gpt-3.5-turbo

    references to news articles or news-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sweat
    -0.76
     cold
    -0.72
     slee
    -0.71
     erect
    -0.69
     goddamn
    -0.68
    gged
    -0.67
    angs
    -0.67
    vol
    -0.66
     stagger
    -0.66
    ibr
    -0.65
    POSITIVE LOGITS
    NEWS
    1.10
    news
    1.02
    letters
    1.01
    Reporting
    0.96
    chool
    0.90
    News
    0.87
    letter
    0.86
     headlines
    0.82
    lisher
    0.82
     Coverage
    0.82
    Act Density 0.004%

    No Known Activations