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

    Neuronpedia

    INDEX
    Explanations

    names of people, likely from conversations or dialogue

    oai_token-act-pair · gpt-3.5-turbo

    references to names or organizations, particularly in a dialogue context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.69
    BuyableInstoreAndOnline
    -0.65
     downstream
    -0.65
    gradient
    -0.62
    .","
    -0.61
     Skydragon
    -0.60
    chery
    -0.59
     ),
    -0.59
     consolidation
    -0.58
     dumping
    -0.58
    POSITIVE LOGITS
     laughs
    0.97
    %:
    0.91
    maxwell
    0.87
    ITNESS
    0.79
    Interview
    0.79
    laughs
    0.79
    :
    0.78
    laugh
    0.78
    Answer
    0.76
     laughed
    0.75
    Act Density 0.151%

    No Known Activations