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

    Neuronpedia

    INDEX
    Explanations

    mentions of doses or dosage of medication or substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medication dosage and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.86
    kees
    -0.81
    inates
    -0.80
    rade
    -0.72
    pora
    -0.70
    league
    -0.70
    atters
    -0.67
    ger
    -0.66
    orem
    -0.66
    istics
    -0.66
    POSITIVE LOGITS
     dose
    1.14
     doses
    1.06
     regimen
    1.06
     dosage
    1.06
     orally
    1.00
     inhal
    0.91
     intraven
    0.90
     nicotine
    0.89
     aspirin
    0.88
     Dos
    0.85
    Act Density 0.063%

    No Known Activations