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

    Neuronpedia

    INDEX
    Explanations

    concepts related to irony and absurdity

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to irony and absurdity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergy
    -0.82
    ved
    -0.76
    arters
    -0.67
    estone
    -0.67
    ves
    -0.65
    ving
    -0.64
    vy
    -0.64
    reditary
    -0.64
    inent
    -0.63
    Interstitial
    -0.63
    POSITIVE LOGITS
    uality
    0.84
     juxtap
    0.83
     irony
    0.80
     avoidance
    0.78
     guiActiveUn
    0.77
     attRot
    0.76
    ĸļ
    0.75
    ously
    0.75
    iness
    0.74
    xtap
    0.73
    Act Density 0.019%

    No Known Activations