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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically the name "Kay"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kay"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urally
    -0.71
     mund
    -0.64
     Inquis
    -0.63
    inous
    -0.60
    æł
    -0.58
    naires
    -0.58
     Brotherhood
    -0.58
     sequ
    -0.58
     atmosp
    -0.57
     oxide
    -0.55
    POSITIVE LOGITS
    la
    1.24
    leigh
    1.17
    von
    1.05
    aking
    1.03
    den
    1.00
    lus
    0.99
    lie
    0.98
    lee
    0.98
    enne
    0.94
    asin
    0.94
    Act Density 0.040%

    No Known Activations