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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "processed."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of processed foods and their health implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Powers
    -0.76
    ettings
    -0.73
    lihood
    -0.72
     Pact
    -0.70
    ods
    -0.70
     Talent
    -0.70
    ilities
    -0.69
     Writers
    -0.69
     Dev
    -0.68
    pring
    -0.67
    POSITIVE LOGITS
     processed
    3.57
     packaged
    1.36
     refined
    1.34
     scanned
    1.33
     filtered
    1.29
     parsed
    1.27
     retrieved
    1.23
     harvested
    1.23
     saturated
    1.20
     analyzed
    1.18
    Act Density 0.016%

    No Known Activations