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

    Neuronpedia

    INDEX
    Explanations

    mentions of 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
    -0.78
    ournal
    -0.69
    Interstitial
    -0.68
    ansky
    -0.66
    urat
    -0.65
    amber
    -0.65
    arta
    -0.65
    yang
    -0.65
     Parables
    -0.64
    reads
    -0.64
    POSITIVE LOGITS
     fuels
    1.27
     fuel
    1.11
    ized
    1.05
    fuel
    1.01
    ifer
    0.97
     footprints
    0.93
    ization
    0.93
     fossil
    0.89
    izers
    0.88
     dioxide
    0.87
    Act Density 0.022%

    No Known Activations