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

    Neuronpedia

    INDEX
    Explanations

    mentions of and related to fossil fuels

    oai_token-act-pair · gpt-3.5-turbo

    references to fossil fuels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.85
    arta
    -0.81
    ynski
    -0.76
    ournal
    -0.75
     Norton
    -0.73
    yang
    -0.67
    amber
    -0.66
     Wilkinson
    -0.66
    Contact
    -0.65
    subject
    -0.65
    POSITIVE LOGITS
     fuels
    1.04
     fossil
    1.02
     fuel
    0.97
    ized
    0.90
     Foss
    0.88
     footprints
    0.83
    ifer
    0.80
    fuel
    0.79
    ocene
    0.78
     fossils
    0.77
    Act Density 0.008%

    No Known Activations