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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opting out of agreements or services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to options or choices in agreements and consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pulp
    -0.66
     Henderson
    -0.65
     Rath
    -0.63
     bis
    -0.62
     Hunger
    -0.62
     Moj
    -0.62
     Mour
    -0.61
     Galile
    -0.61
     Burr
    -0.60
     Lau
    -0.60
    POSITIVE LOGITS
    cert
    0.94
    ship
    0.93
    operated
    0.89
    ships
    0.89
    coded
    0.89
    lease
    0.88
    items
    0.88
    ature
    0.87
    to
    0.87
    agent
    0.85
    Act Density 0.106%

    No Known Activations