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

    Neuronpedia

    INDEX
    Explanations

    medical terms or health-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related terminology and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oÄŁ
    -0.80
    inventoryQuantity
    -0.77
    unci
    -0.71
    itive
    -0.61
    609
    -0.61
    cair
    -0.61
    rogen
    -0.60
    lvl
    -0.59
    erning
    -0.59
    509
    -0.58
    POSITIVE LOGITS
    deen
    0.78
     Revenge
    0.68
     Quest
    0.64
     Dictionary
    0.63
     Mutual
    0.62
     Club
    0.61
    aughters
    0.61
     Dinner
    0.60
    reed
    0.59
    ochond
    0.59
    Act Density 0.205%

    No Known Activations