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

    Neuronpedia

    INDEX
    Explanations

    mentions of sources of light

    oai_token-act-pair · gpt-3.5-turbo

    references to lights in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llah
    -0.79
    culosis
    -0.78
    xit
    -0.76
    ilage
    -0.69
    xus
    -0.67
    lyak
    -0.66
    utor
    -0.64
    doms
    -0.64
     Bundy
    -0.62
    ois
    -0.62
    POSITIVE LOGITS
     bulbs
    1.37
     bulb
    1.34
     fixtures
    1.10
    bul
    1.07
     fixture
    1.07
     illuminate
    1.05
     illuminating
    1.04
    lights
    1.02
     emitting
    1.02
     lamps
    1.02
    Act Density 0.047%

    No Known Activations