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

    Neuronpedia

    INDEX
    Explanations

    articles or content related to news events or stories

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "RELATED" and other similar labels or tags in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.85
    76561
    -0.78
    angers
    -0.73
    amping
    -0.71
    apers
    -0.71
    udi
    -0.70
    atur
    -0.70
    animate
    -0.70
    ctrl
    -0.68
    oise
    -0.68
    POSITIVE LOGITS
     VIDEOS
    1.13
     IMAGES
    1.13
     INFORMATION
    1.08
     STOR
    0.97
    RELATED
    0.96
     ARTICLE
    0.95
     STORY
    0.92
     LINK
    0.88
    ...]
    0.87
     ALSO
    0.87
    Act Density 0.011%

    No Known Activations