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

    Neuronpedia

    INDEX
    Explanations

    the name "Luke" occurring in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Luke."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ú
    -0.71
    ifice
    -0.69
    Ö¼
    -0.66
     WATCHED
    -0.63
    itect
    -0.63
    icient
    -0.63
    ãĤ¡
    -0.62
    ursed
    -0.61
    ãĤ¢ãĥ«
    -0.61
    uration
    -0.61
    POSITIVE LOGITS
     Skywalker
    1.34
    warm
    1.34
     Cage
    1.02
    lihood
    0.96
     Walton
    0.80
     Somers
    0.78
     Daniels
    0.75
    avin
    0.74
    nuts
    0.72
    hart
    0.72
    Act Density 0.019%

    No Known Activations