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

    Neuronpedia

    INDEX
    Explanations

    words related to light, brightness, illumination, and light sources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to light and illumination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xia
    -0.88
    eln
    -0.86
    keye
    -0.83
    remlin
    -0.78
    ryu
    -0.76
    culosis
    -0.74
    ties
    -0.74
    zip
    -0.73
    CHA
    -0.73
    cha
    -0.71
    POSITIVE LOGITS
     illuminated
    1.07
     bulbs
    1.00
     illuminating
    0.99
     lamps
    0.97
     illuminate
    0.96
     orbs
    0.94
     shone
    0.93
    orescence
    0.92
     lights
    0.89
     Lights
    0.88
    Act Density 0.020%

    No Known Activations