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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "pun" and its variations, indicating a focus on humor or wordplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dz
    -0.19
    444
    -0.17
    pheres
    -0.15
    ãĤĦãģĻ
    -0.15
    uben
    -0.15
    ิà¸ĩห
    -0.15
    den
    -0.14
    ãĤĵãģ©
    -0.14
    irez
    -0.14
    adden
    -0.14
    POSITIVE LOGITS
    jabi
    0.34
    ishment
    0.26
    isher
    0.26
    pun
    0.25
    ishments
    0.24
     intended
    0.24
    jab
    0.24
     Pun
    0.21
    ishing
    0.21
     pun
    0.21
    Act Density 0.006%

    No Known Activations