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

    Neuronpedia

    INDEX
    Explanations

    mentions of medical terms or entities such as "Med", "NHS", "MyMed", and "medical conditions"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Med" related to medical or healthcare contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     innocence
    -0.69
    !/
    -0.65
    ¯
    -0.64
    âĻ¦
    -0.64
    ¯
    -0.62
     indign
    -0.61
    BOOK
    -0.61
     Grayson
    -0.60
     Orwell
    -0.60
    ï¸ı
    -0.60
    POSITIVE LOGITS
    Med
    1.26
    iterranean
    1.19
    ieval
    1.17
    ications
    1.09
    undai
    1.06
    icum
    0.95
    ics
    0.92
    ication
    0.89
    phrine
    0.89
    eco
    0.88
    Act Density 0.005%

    No Known Activations