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

    Neuronpedia

    INDEX
    Explanations

    captions or labels for images or photographs

    oai_token-act-pair · gpt-3.5-turbo

    instances of image captions and related commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incorpor
    -0.80
    bats
    -0.79
    nesia
    -0.78
     pestic
    -0.77
     illegitimate
    -0.72
     satell
    -0.71
    ĪĴ
    -0.70
    rency
    -0.70
     rejuven
    -0.65
     unsett
    -0.65
    POSITIVE LOGITS
     Courtesy
    1.08
     toggle
    0.99
     Photograph
    0.82
    Enlarge
    0.79
     ï
    0.78
     AFP
    0.73
     REUTERS
    0.72
     Pinterest
    0.72
     Image
    0.71
    advertisement
    0.71
    Act Density 0.005%

    No Known Activations