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

    Neuronpedia

    INDEX
    Explanations

    phrases related to photographs with high activation value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "photos" in various forms or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.79
     bye
    -0.68
     whistle
    -0.67
    vernment
    -0.65
    appa
    -0.64
     gravity
    -0.64
    grass
    -0.64
     speech
    -0.62
    rule
    -0.61
    ismo
    -0.60
    POSITIVE LOGITS
    PHOTOS
    1.12
     IMAGES
    1.10
     VIDEOS
    1.06
     Images
    1.05
    Photos
    1.05
    Images
    0.96
    photos
    0.91
     Photos
    0.91
     PHOTO
    0.85
    Gallery
    0.83
    Act Density 0.016%

    No Known Activations