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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles and dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to news outlets and media organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Draper
    -0.86
     Goldberg
    -0.79
     Painter
    -0.76
     Faust
    -0.76
     Griffin
    -0.76
     captcha
    -0.76
     Professor
    -0.75
     Yose
    -0.75
     Morty
    -0.74
     Hollow
    -0.72
    POSITIVE LOGITS
    Official
    1.07
    HQ
    1.04
    official
    1.00
    news
    0.94
    _
    0.91
    gov
    0.90
    euro
    0.88
    podcast
    0.86
    Europe
    0.86
    network
    0.86
    Act Density 0.095%

    No Known Activations