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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "oil"

    oai_token-act-pair · gpt-3.5-turbo

    references to the oil industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enance
    -0.85
    RON
    -0.83
    rons
    -0.82
     Inv
    -0.80
     Dare
    -0.75
    BY
    -0.74
     Cox
    -0.74
    EMBER
    -0.73
    é¾įå
    -0.73
     Try
    -0.72
    POSITIVE LOGITS
     oil
    1.21
    Oil
    1.02
    seed
    1.01
    oil
    1.00
     slic
    0.99
     Oil
    0.96
     sands
    0.94
     tanker
    0.88
     drilling
    0.88
     refining
    0.88
    Act Density 0.016%

    No Known Activations