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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    oai_token-act-pair · gpt-3.5-turbo

    references to blogs or blog posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.77
     Lauder
    -0.72
    odka
    -0.71
    emale
    -0.70
     Baal
    -0.69
     Scotia
    -0.67
     Lann
    -0.66
    inho
    -0.65
     evils
    -0.65
    TRUMP
    -0.65
    POSITIVE LOGITS
    osphere
    1.22
    gers
    1.07
    post
    1.03
    ging
    0.98
    ged
    0.98
    blogs
    0.94
     postings
    0.89
    ger
    0.89
    posts
    0.88
    gments
    0.88
    Act Density 0.021%

    No Known Activations