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

    Neuronpedia

    INDEX
    Explanations

    mentions of emissions, particularly those related to human activity and environmental impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental emissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Else
    -1.00
    Otherwise
    -0.78
     Acqu
    -0.76
    Boss
    -0.75
    ISH
    -0.71
    \":
    -0.71
    OVA
    -0.69
    si
    -0.69
     Else
    -0.68
    rooms
    -0.68
    POSITIVE LOGITS
     emissions
    1.36
     emission
    1.20
     emitting
    0.96
     dioxide
    0.95
     pollution
    0.92
     pollutants
    0.86
     emit
    0.85
     emitted
    0.85
     pollut
    0.85
     gases
    0.83
    Act Density 0.016%

    No Known Activations