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

    Neuronpedia

    INDEX
    Explanations

    chemical elements and compounds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of oxygen in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awar
    -0.87
    enegger
    -0.85
    erers
    -0.80
    ochet
    -0.79
    invoke
    -0.77
    erer
    -0.74
    aji
    -0.72
    achu
    -0.70
    eret
    -0.69
     Judgment
    -0.69
    POSITIVE LOGITS
     oxygen
    0.94
     isot
    0.94
     dioxide
    0.92
    ated
    0.88
     uptake
    0.87
     saturation
    0.86
     inhal
    0.86
     consumption
    0.82
     flow
    0.80
     absor
    0.79
    Act Density 0.029%

    No Known Activations