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

    Neuronpedia

    INDEX
    Explanations

    captions under images in text

    oai_token-act-pair · gpt-3.5-turbo

    references to image captions and their associated functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nu
    -0.74
     effected
    -0.65
     stakes
    -0.63
    bats
    -0.63
     tense
    -0.62
     unsuccessful
    -0.62
    milo
    -0.61
     expended
    -0.61
     assum
    -0.59
    phi
    -0.59
    POSITIVE LOGITS
     Transcript
    0.96
    Enlarge
    0.93
    toggle
    0.93
     Courtesy
    0.91
     Thumbnails
    0.88
    advertisement
    0.81
     Archdemon
    0.80
     toggle
    0.80
     Annotations
    0.80
    acters
    0.79
    Act Density 0.012%

    No Known Activations