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

    Neuronpedia

    INDEX
    Explanations

    references to fossil fuels

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fossil fuels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.93
    arta
    -0.78
    ansky
    -0.78
    yang
    -0.77
    amber
    -0.71
    OA
    -0.71
    Interstitial
    -0.70
    thel
    -0.69
     Norton
    -0.69
    urat
    -0.68
    POSITIVE LOGITS
     fuels
    1.14
     fuel
    1.05
    ized
    1.01
     fossil
    0.95
    ization
    0.89
     footprints
    0.88
    fuel
    0.88
    ifer
    0.87
     Foss
    0.84
    itions
    0.82
    Act Density 0.013%

    No Known Activations