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

    Neuronpedia

    INDEX
    Explanations

    instances of jokes and humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.56
    MBR
    -0.49
     MBR
    -0.49
     Whitby
    -0.47
     SSR
    -0.47
     CBI
    -0.46
     CRS
    -0.46
     PMI
    -0.46
     McMaster
    -0.45
     SBR
    -0.45
    POSITIVE LOGITS
     jokes
    1.84
     joke
    1.84
    joke
    1.66
     Joke
    1.63
     Jokes
    1.59
    jokes
    1.57
    Jokes
    1.56
    Joke
    1.52
     joking
    1.38
     joked
    1.31
    Act Density 0.002%

    No Known Activations