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

    Neuronpedia

    INDEX
    Explanations

    mentions of the human body

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term 'body.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kafka
    -0.77
     Clover
    -0.66
     Nex
    -0.65
     Dickens
    -0.65
    BILITY
    -0.64
     Hoover
    -0.64
     Ans
    -0.64
     Monthly
    -0.62
     Liberty
    -0.61
     PBS
    -0.61
    POSITIVE LOGITS
    guards
    1.13
    anguage
    1.04
    builder
    0.99
    builders
    0.97
    body
    0.97
    fat
    0.92
    weight
    0.90
     body
    0.89
    guard
    0.89
    parts
    0.86
    Act Density 0.021%

    No Known Activations