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

    Neuronpedia

    INDEX
    Explanations

    references to extensive or detailed content in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "extensive."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CENT
    -0.77
    crow
    -0.74
    pal
    -0.73
    earth
    -0.71
    Earth
    -0.71
    iman
    -0.70
    instead
    -0.69
    opers
    -0.68
    girls
    -0.68
    Frames
    -0.67
    POSITIVE LOGITS
    mble
    0.87
     amounts
    0.84
    ãĤ£
    0.79
     detail
    0.74
     coverage
    0.73
     schooling
    0.71
     enough
    0.70
     customization
    0.68
    bred
    0.68
     structural
    0.67
    Act Density 0.025%

    No Known Activations