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

    Neuronpedia

    INDEX
    Explanations

    photo captions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Photo" indicating visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imore
    -0.76
    iazep
    -0.75
    cffff
    -0.74
    uckle
    -0.73
    riched
    -0.70
    resses
    -0.69
    acebook
    -0.69
    adden
    -0.69
    ollah
    -0.68
    otomy
    -0.68
    POSITIVE LOGITS
     illustration
    0.79
    journal
    0.77
     Gallery
    0.75
    Shop
    0.75
     snapped
    0.72
     gallery
    0.72
     shoots
    0.71
     credit
    0.70
     Photo
    0.70
     galleries
    0.69
    Act Density 0.015%

    No Known Activations