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

    Neuronpedia

    INDEX
    Explanations

    words related to importance or prominence in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate centrality or significance, particularly using the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TION
    -0.67
    asha
    -0.67
    aday
    -0.66
    ulia
    -0.65
    crew
    -0.65
    notation
    -0.63
     SHARES
    -0.62
    ription
    -0.62
    cum
    -0.61
     Norn
    -0.61
    POSITIVE LOGITS
     forefront
    1.61
     helm
    1.41
     mercy
    1.37
     heart
    1.14
     centre
    1.14
     pinnacle
    1.13
     center
    1.13
     disposal
    1.11
     beck
    1.10
     nexus
    1.08
    Act Density 0.088%

    No Known Activations