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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a specific action taken for a particular purpose

    oai_token-act-pair · gpt-3.5-turbo

    the adverb "just."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Responsibility
    -0.65
    aea
    -0.61
     elders
    -0.58
    Topics
    -0.58
    ahime
    -0.57
    pora
    -0.57
    nation
    -0.56
     Nurs
    -0.56
     contention
    -0.56
    seek
    -0.55
    POSITIVE LOGITS
    ifications
    1.09
    ifiable
    0.95
    itia
    0.94
    IFIED
    0.84
    ices
    0.82
    IFIC
    0.80
    ifier
    0.78
     kidding
    0.76
    inian
    0.76
    ifying
    0.75
    Act Density 0.061%

    No Known Activations