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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a character named "Luke"

    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
     panc
    -0.73
    aukee
    -0.70
     cartridge
    -0.70
    ÄŁ
    -0.69
    ¢
    -0.68
     perf
    -0.68
    SPA
    -0.66
     salon
    -0.65
     mushroom
    -0.65
    prof
    -0.63
    POSITIVE LOGITS
     Luke
    3.64
    Luke
    3.20
     LU
    1.65
     Leia
    1.61
     Matthew
    1.53
     Lucas
    1.49
     Obi
    1.46
     Vader
    1.46
     Ezra
    1.37
     Darth
    1.35
    Act Density 0.011%

    No Known Activations