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

    Neuronpedia

    INDEX
    Explanations

    specific names, specifically "Lucas," with varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Lucas."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĪ
    -0.70
    req
    -0.69
     reconc
    -0.67
     à¨
    -0.66
    BOOK
    -0.65
    eering
    -0.63
    ifice
    -0.63
    lying
    -0.63
    ħĭ
    -0.63
    lain
    -0.61
    POSITIVE LOGITS
    film
    1.26
    Film
    1.10
     Lucas
    0.93
     Skywalker
    0.93
    ious
    0.87
    ifer
    0.84
    avin
    0.78
    Hunt
    0.76
    afort
    0.76
    eland
    0.76
    Act Density 0.007%

    No Known Activations