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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds or elements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of chemical substances and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.93
     4090
    -0.85
    alos
    -0.85
    stretched
    -0.81
    lest
    -0.80
    shire
    -0.79
    itia
    -0.77
    ership
    -0.77
    zzi
    -0.73
    heit
    -0.73
    POSITIVE LOGITS
     chemical
    1.01
     makeup
    1.00
     compounds
    0.99
     chemicals
    0.96
     substances
    0.95
     additives
    0.93
     chemistry
    0.91
    chemical
    0.90
     warfare
    0.90
     oxide
    0.89
    Act Density 0.018%

    No Known Activations