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

    Neuronpedia

    INDEX
    Explanations

    instances of humor and playful expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     мәкал
    -0.67
    amerikanischer
    -0.63
     européennes
    -0.60
    DockStyle
    -0.59
     سكانية
    -0.59
    ContentValues
    -0.56
    apatkan
    -0.56
     незавершена
    -0.56
    SOUNDBITE
    -0.55
     recommandons
    -0.55
    POSITIVE LOGITS
     joking
    1.31
     joke
    1.30
     joked
    1.18
    joke
    1.07
     Joke
    1.05
    玩笑
    1.05
     jokingly
    1.04
     jokes
    0.99
    Joke
    0.96
    开玩笑
    0.93
    Act Density 0.192%

    No Known Activations