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

    Neuronpedia

    INDEX
    Explanations

    instances of irony or contradiction in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of irony and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.73
    á
    -0.71
    anguages
    -0.70
    ictionary
    -0.69
    tests
    -0.69
    eding
    -0.69
    Beta
    -0.67
    erto
    -0.67
    improve
    -0.66
    XY
    -0.66
    POSITIVE LOGITS
     irony
    1.07
     ironic
    0.94
     Osw
    0.91
     twist
    0.88
     juxtap
    0.88
    netflix
    0.84
     ironically
    0.77
     paradox
    0.77
     mockery
    0.75
     hypocr
    0.74
    Act Density 0.050%

    No Known Activations