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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by captions in a list of photos

    oai_token-act-pair · gpt-3.5-turbo

    references to photo captions or image descriptions in the context of various events and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.61
     enthusi
    -0.59
     disadvant
    -0.58
     Schne
    -0.57
     convenience
    -0.57
    ntil
    -0.57
    Condition
    -0.55
    sembly
    -0.54
     Wonderland
    -0.54
     denial
    -0.54
    POSITIVE LOGITS
    embed
    0.71
    iman
    0.70
    wcsstore
    0.66
     Photos
    0.65
     embed
    0.64
     caption
    0.63
    ĵ
    0.61
    Gallery
    0.61
     Pict
    0.60
     captcha
    0.60
    Act Density 0.014%

    No Known Activations