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

    Neuronpedia

    INDEX
    Explanations

    humorous and comedic elements in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignty
    -0.81
    ports
    -0.76
    eus
    -0.71
    arching
    -0.71
    ignt
    -0.70
    ainer
    -0.69
    hips
    -0.69
    axies
    -0.65
    arnaev
    -0.65
    uchs
    -0.65
    POSITIVE LOGITS
    ously
    0.96
    netflix
    0.93
     jokes
    0.87
     mocking
    0.85
     banter
    0.82
    writer
    0.82
     comedian
    0.79
     roast
    0.78
    writers
    0.77
     humour
    0.77
    Act Density 0.169%

    No Known Activations