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

    Neuronpedia

    INDEX
    Explanations

    blocks of text containing multiple connected ideas or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -1.00
     Cust
    -0.69
    ocked
    -0.67
     Veter
    -0.66
     Profile
    -0.62
    ivo
    -0.61
    aque
    -0.61
    fecture
    -0.61
    BP
    -0.61
    ipop
    -0.60
    POSITIVE LOGITS
     ideas
    3.56
     Ideas
    2.65
     concepts
    2.08
     idea
    2.03
     notions
    2.01
     suggestions
    1.85
     Idea
    1.82
     thoughts
    1.73
     ideals
    1.73
     theories
    1.70
    Act Density 0.019%

    No Known Activations