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

    Neuronpedia

    INDEX
    Explanations

    photographers' names mentioned in captions

    oai_token-act-pair · gpt-3.5-turbo

    the attribution of images or captions to specific photographers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antle
    -0.71
     noses
    -0.70
    iqueness
    -0.69
    ighth
    -0.67
    uality
    -0.67
    phrine
    -0.65
     truths
    -0.64
    rums
    -0.63
    iosity
    -0.63
    ulnerable
    -0.63
    POSITIVE LOGITS
     Evan
    1.00
     Pablo
    0.98
     Shutterstock
    0.96
     Erik
    0.94
     Karin
    0.92
     Kathryn
    0.91
     Flickr
    0.89
     Kev
    0.88
     Danielle
    0.88
     REUTERS
    0.88
    Act Density 0.026%

    No Known Activations