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

    Neuronpedia

    INDEX
    Explanations

    the phrase "what the [expletive]" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "what the [expletive]"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighthouse
    -0.82
    alus
    -0.80
    arate
    -0.79
    thood
    -0.78
    afe
    -0.77
    icia
    -0.75
    chery
    -0.75
    earances
    -0.72
    iband
    -0.72
    auri
    -0.71
    POSITIVE LOGITS
     heck
    1.20
    ses
    1.05
     slightest
    1.03
     hell
    1.00
     difference
    0.98
     greatest
    0.93
     proverbial
    0.92
     likes
    0.90
     fuss
    0.90
     outcome
    0.90
    Act Density 0.117%

    No Known Activations