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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or handles on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    specific names and references related to people, places, or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     triglycer
    -0.59
    hetically
    -0.57
     runoff
    -0.57
     metab
    -0.55
     recru
    -0.55
    idis
    -0.54
    gall
    -0.53
    terness
    -0.52
     conclud
    -0.51
    Ïģ
    -0.51
    POSITIVE LOGITS
    issance
    0.75
    enment
    0.62
     Wonderland
    0.60
    enegger
    0.59
     Corpus
    0.59
    bush
    0.58
    liga
    0.57
    ois
    0.57
    shire
    0.57
     Garland
    0.54
    Act Density 1.182%

    No Known Activations