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

    Neuronpedia

    INDEX
    Explanations

    puns in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pun"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ACS
    -0.83
     Lens
    -0.72
    enza
    -0.72
     UNCLASSIFIED
    -0.71
     Chamberlain
    -0.71
    Documents
    -0.70
     Emerging
    -0.68
    atham
    -0.67
    acs
    -0.67
     Origins
    -0.66
    POSITIVE LOGITS
     pun
    3.98
    pun
    1.98
     punt
    1.86
     Pun
    1.66
     kicker
    1.28
     jokes
    1.20
     gif
    1.09
     discrim
    1.03
     penal
    1.01
     joke
    1.01
    Act Density 0.014%

    No Known Activations