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

    Neuronpedia

    INDEX
    Explanations

    references to different news sources and media outlets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news organizations and their publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaveral
    -0.65
     wrists
    -0.60
     Lans
    -0.58
     enroll
    -0.58
     waivers
    -0.57
    hops
    -0.56
    itures
    -0.55
     necks
    -0.55
     causation
    -0.55
     interpretations
    -0.54
    POSITIVE LOGITS
     Observer
    0.76
     Blog
    0.73
    Hour
    0.71
    osphere
    0.71
     Tribune
    0.70
    icter
    0.70
    atmeal
    0.70
     Encyclopedia
    0.70
    isky
    0.69
    Journal
    0.69
    Act Density 0.102%

    No Known Activations