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

    Neuronpedia

    INDEX
    Explanations

    screenshots in text

    oai_token-act-pair · gpt-3.5-turbo

    references to screenshots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iott
    -0.85
    neg
    -0.75
    doms
    -0.72
    church
    -0.70
    vet
    -0.67
    trust
    -0.66
    profits
    -0.65
     promoter
    -0.65
    ternity
    -0.64
    uct
    -0.64
    POSITIVE LOGITS
    reenshot
    1.31
     screenshots
    1.10
     screenshot
    1.08
    reenshots
    1.05
    Screenshot
    0.96
     Thumbnails
    0.83
     pics
    0.80
     IMAGES
    0.80
    photos
    0.79
    Pict
    0.77
    Act Density 0.012%

    No Known Activations