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

    Neuronpedia

    INDEX
    Explanations

    references to carbon dioxide (CO2) and related chemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GRAF
    -0.65
    й
    -0.62
     ép
    -0.61
     Apoll
    -0.60
     접
    -0.55
    Kow
    -0.55
    ไล
    -0.54
     Greif
    -0.52
     WET
    -0.52
     Agua
    -0.52
    POSITIVE LOGITS
     CO
    2.23
    CO
    1.85
     dioxide
    1.32
     monoxide
    1.31
     Dioxide
    1.26
    anyahu
    1.13
    Colorado
    1.01
    COG
    1.00
     Greenhouse
    0.98
     Carney
    0.95
    Act Density 0.187%

    No Known Activations