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

    Neuronpedia

    INDEX
    Explanations

    information related to news conferences

    oai_token-act-pair · gpt-3.5-turbo

    references to news conferences or news-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.76
    ength
    -0.71
    sei
    -0.70
    ippery
    -0.69
    struction
    -0.66
    ayne
    -0.66
    aughs
    -0.66
    inho
    -0.65
    ause
    -0.65
     Mississ
    -0.64
    POSITIVE LOGITS
    reader
    1.09
    worthy
    0.99
    room
    0.96
    agent
    0.94
    worthiness
    0.90
    print
    0.89
    flash
    0.88
    feed
    0.87
    agents
    0.87
    agency
    0.86
    Act Density 0.036%

    No Known Activations