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

    Neuronpedia

    INDEX
    Explanations

    references to news articles or pieces of news

    oai_token-act-pair · gpt-3.5-turbo

    references to various sources or citations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accordingly
    -0.72
     disgu
    -0.69
     record
    -0.67
     prey
    -0.67
     aside
    -0.65
     rug
    -0.65
     advert
    -0.63
     lapse
    -0.62
     proced
    -0.62
     sooner
    -0.62
    POSITIVE LOGITS
    AFP
    1.06
    Getty
    1.06
    Courtesy
    1.05
    Flickr
    1.04
    ËĪ
    1.00
    Bloomberg
    0.96
    CBC
    0.91
    etc
    0.89
    Library
    0.87
    HT
    0.85
    Act Density 0.027%

    No Known Activations