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

    Neuronpedia

    INDEX
    Explanations

    references to images in articles or blog posts

    oai_token-act-pair · gpt-3.5-turbo

    references to images or visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    effect
    -0.70
    cffffcc
    -0.67
    )",
    -0.64
    emet
    -0.62
    é¾į
    -0.61
    called
    -0.59
    umbers
    -0.57
    onse
    -0.57
    bably
    -0.57
    bia
    -0.57
    POSITIVE LOGITS
    <|endoftext|>
    1.28
    Featured
    1.13
    Advertisements
    1.10
     Comments
    1.04
    Comments
    0.98
     Tags
    0.95
     Featured
    0.95
    Follow
    0.89
     Credits
    0.89
    Edited
    0.88
    Act Density 0.310%

    No Known Activations