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

    Neuronpedia

    INDEX
    Explanations

    information related to articles or photos

    oai_token-act-pair · gpt-3.5-turbo

    mentions of photo-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.87
    stood
    -0.79
    pling
    -0.74
     congress
    -0.73
    ught
    -0.71
     bargain
    -0.70
    ressive
    -0.67
     homeland
    -0.66
     nonviolent
    -0.66
     denomin
    -0.66
    POSITIVE LOGITS
    Photos
    1.49
    ynthesis
    1.19
     Photos
    1.15
     Caption
    1.04
     Thumbnails
    1.03
    Images
    0.96
    OTOS
    0.95
     Photo
    0.91
    Gallery
    0.91
    ynt
    0.90
    Act Density 0.006%

    No Known Activations