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

    Neuronpedia

    INDEX
    Explanations

    captions or labels beneath images that require attention or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of image captions and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesia
    -0.80
    ĪĴ
    -0.78
    etheless
    -0.78
     illegitimate
    -0.73
     incorpor
    -0.73
     unsett
    -0.69
    bats
    -0.68
     pestic
    -0.68
    warm
    -0.67
    urg
    -0.67
    POSITIVE LOGITS
     Courtesy
    1.10
     toggle
    0.93
     Photograph
    0.85
     Shutterstock
    0.81
     Kev
    0.80
     Image
    0.79
     COURT
    0.79
     IMAGES
    0.79
     screenshot
    0.77
     Thumbnails
    0.76
    Act Density 0.008%

    No Known Activations