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

    Neuronpedia

    INDEX
    Explanations

    information related to recent news and developments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news-related events or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ause
    -0.76
    orney
    -0.76
    asus
    -0.71
    orsi
    -0.70
     inh
    -0.70
    ental
    -0.69
    tein
    -0.69
    asse
    -0.69
    inances
    -0.68
    rylic
    -0.68
    POSITIVE LOGITS
    worthiness
    1.12
    reader
    0.96
    worthy
    0.96
    flash
    0.95
    agents
    0.84
    room
    0.79
     announcement
    0.78
    print
    0.75
     announcements
    0.73
    feed
    0.73
    Act Density 0.055%

    No Known Activations