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

    Neuronpedia

    INDEX
    Explanations

    references to news articles, websites, and public policy documents

    oai_token-act-pair · gpt-3.5-turbo

    URLs or links related to news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sinai
    -0.70
     Rhodes
    -0.66
     Yel
    -0.65
     ÂŃ
    -0.65
     Oval
    -0.62
     mouths
    -0.61
     compounded
    -0.60
     Dull
    -0.60
     «
    -0.59
     Reed
    -0.59
    POSITIVE LOGITS
    /)
    1.14
    /,
    1.06
    /?
    1.03
    /.
    1.03
    /#
    0.97
    ascript
    0.96
    _
    0.92
    /_
    0.90
    utorial
    0.86
    _-_
    0.83
    Act Density 0.078%

    No Known Activations