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

    Neuronpedia

    INDEX
    Explanations

    references to fossil fuel and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gross
    -0.15
    ings
    -0.15
    er
    -0.15
    nown
    -0.15
    .fhir
    -0.15
    ht
    -0.14
    atori
    -0.14
    tures
    -0.14
    ement
    -0.14
    innen
    -0.14
    POSITIVE LOGITS
     fuels
    0.39
     fuel
    0.38
    fuel
    0.32
     Fuel
    0.30
     Fu
    0.29
    çĩĥ
    0.29
    Fuel
    0.29
     fueled
    0.26
    ifer
    0.22
    ized
    0.20
    Act Density 0.006%

    No Known Activations