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

    Neuronpedia

    INDEX
    Explanations

    specific patterns of numbers related to various events or stories such as "Back to Gallery" references followed by numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    specific numeric identifiers or references in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebook
    -0.65
     theoret
    -0.63
    vik
    -0.62
    oret
    -0.61
     seiz
    -0.61
    worms
    -0.58
     wisely
    -0.57
     iod
    -0.56
     overpowered
    -0.55
     benef
    -0.55
    POSITIVE LOGITS
    thumbnails
    0.88
     Close
    0.83
     Gallery
    0.81
     Thumbnails
    0.79
    Photo
    0.78
    Photos
    0.76
     FILE
    0.72
     Photos
    0.72
     Caption
    0.70
    ategories
    0.67
    Act Density 0.037%

    No Known Activations