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

    Neuronpedia

    INDEX
    Explanations

    measurements related to health and bodily functions

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements related to blood-related health metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orno
    -0.69
    ovie
    -0.69
    etheless
    -0.65
    purpose
    -0.64
    oeuv
    -0.63
    film
    -0.63
    ItemImage
    -0.63
     embod
    -0.62
     Identity
    -0.62
    sonian
    -0.62
    POSITIVE LOGITS
     skyrocket
    1.53
     plummet
    1.41
     plummeted
    1.29
     soared
    1.23
     spike
    1.22
     spikes
    1.21
     increase
    1.21
     increased
    1.21
     soar
    1.20
     decreased
    1.20
    Act Density 0.464%

    No Known Activations