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

    Neuronpedia

    INDEX
    Explanations

    phrases that prompt the reader to consider different perspectives or framing of concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "think of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pite
    -0.70
     promoter
    -0.61
    ollah
    -0.60
    ante
    -0.60
     proclaimed
    -0.59
    Written
    -0.59
     maintained
    -0.59
     differed
    -0.58
    Tweet
    -0.58
    Found
    -0.58
    POSITIVE LOGITS
    èĪ
    0.69
    buck
    0.63
    agine
    0.63
    agus
    0.62
     quitting
    0.61
    abel
    0.61
     è£ıè
    0.61
    agram
    0.61
    gil
    0.60
    swer
    0.60
    Act Density 0.054%

    No Known Activations