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

    Neuronpedia

    INDEX
    Explanations

    food-related items such as items of food or ingredients

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate alternatives or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ires
    -0.79
    ocrats
    -0.71
    OTAL
    -0.66
    enko
    -0.63
    qqa
    -0.63
    ETS
    -0.62
    igned
    -0.61
    masters
    -0.60
    IGHTS
    -0.60
    yet
    -0.59
    POSITIVE LOGITS
    acle
    1.27
    ifice
    1.21
    chid
    1.21
    chard
    1.17
    acles
    1.13
    Else
    1.11
    nam
    1.11
    lando
    1.04
    whatever
    1.02
    acular
    1.00
    Act Density 0.162%

    No Known Activations