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

    Neuronpedia

    INDEX
    Explanations

    references to agents in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Krie
    -0.79
     Leck
    -0.73
    Thur
    -0.72
    ERICK
    -0.71
    prehension
    -0.71
     bifur
    -0.71
    ths
    -0.71
     BeautifulSoup
    -0.70
    Sébastien
    -0.69
     Fino
    -0.69
    POSITIVE LOGITS
     agents
    2.00
     Agents
    1.92
     agent
    1.90
     Agent
    1.83
    Agents
    1.82
     AGENT
    1.77
    Agent
    1.77
    agents
    1.71
     AGENTS
    1.71
    AGENT
    1.69
    Act Density 0.103%

    No Known Activations