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

    Neuronpedia

    INDEX
    Explanations

    mentions of the element oxygen

    oai_token-act-pair · gpt-3.5-turbo

    references to oxygen and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awar
    -0.79
    doms
    -0.71
    enegger
    -0.68
    practice
    -0.67
    quartered
    -0.66
    invoke
    -0.65
    ochet
    -0.64
    prototype
    -0.64
    GAME
    -0.64
     Tale
    -0.63
    POSITIVE LOGITS
    ated
    1.21
     dioxide
    1.16
    ation
    1.15
    ating
    1.07
     uptake
    1.02
     oxygen
    0.98
     isot
    0.97
     saturation
    0.95
     deprivation
    0.92
     atoms
    0.90
    Act Density 0.051%

    No Known Activations