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

    Neuronpedia

    INDEX
    Explanations

    words related to doses and toxicity

    oai_token-act-pair · gpt-3.5-turbo

    references to drug doses and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inates
    -0.73
    aldi
    -0.70
    kees
    -0.68
    ovies
    -0.67
    American
    -0.66
    atters
    -0.65
    adia
    -0.64
    rade
    -0.63
    ondon
    -0.62
    colonial
    -0.62
    POSITIVE LOGITS
     dose
    1.14
     doses
    0.96
     regimen
    0.94
     dosage
    0.90
     inhal
    0.83
     orally
    0.81
     aspirin
    0.71
     laced
    0.70
     weights
    0.70
     ingested
    0.70
    Act Density 0.031%

    No Known Activations