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

    Neuronpedia

    INDEX
    Explanations

    phrases containing wordplay or puns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pun" and variations related to humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Apostles
    -0.64
     Frankfurt
    -0.60
     Archdemon
    -0.59
     Close
    -0.56
     Resurrection
    -0.55
    Newsletter
    -0.54
     Frie
    -0.54
    008
    -0.54
    ({
    -0.54
     Brill
    -0.53
    POSITIVE LOGITS
    ishers
    1.41
    isher
    1.33
    ishes
    1.19
    cheon
    1.16
    ishment
    1.12
    cher
    1.11
    jab
    1.07
    pun
    1.07
    xs
    1.07
    itiveness
    1.06
    Act Density 0.032%

    No Known Activations