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

    Neuronpedia

    INDEX
    Explanations

    phrases related to general statements or observations about people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating generalizations about people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )].
    -0.76
     Skydragon
    -0.74
     SetTextColor
    -0.73
    cloth
    -0.69
    iang
    -0.64
    ="/
    -0.64
     Void
    -0.64
     Demonic
    -0.64
    inders
    -0.62
    cule
    -0.61
    POSITIVE LOGITS
     anymore
    0.74
    asio
    0.70
    YP
    0.67
    irlf
    0.64
     answ
    0.61
     appe
    0.60
     penny
    0.60
     sugg
    0.60
     nor
    0.59
     fortun
    0.58
    Act Density 0.035%

    No Known Activations