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

    Neuronpedia

    INDEX
    Explanations

    mentions of chemistry and chemical-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to chemistry and its various applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.75
    agle
    -0.72
    ittle
    -0.70
    cise
    -0.70
    early
    -0.70
    fty
    -0.69
    clusive
    -0.66
    por
    -0.66
    grim
    -0.65
    avement
    -0.63
    POSITIVE LOGITS
     chemistry
    1.43
    istry
    1.06
     Chemistry
    0.97
     chemist
    0.95
    Chem
    0.88
    odynamics
    0.86
    chem
    0.85
    ochemistry
    0.78
    istries
    0.78
     potions
    0.77
    Act Density 0.011%

    No Known Activations