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

    Neuronpedia

    INDEX
    Explanations

    mentions or descriptions of light.

    oai_token-act-pair · gpt-3.5-turbo

    references to light

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettings
    -0.79
    halla
    -0.74
    ublic
    -0.74
    sburgh
    -0.72
    berus
    -0.72
    OAD
    -0.70
     Fas
    -0.70
    rolet
    -0.70
    llah
    -0.69
    monary
    -0.67
    POSITIVE LOGITS
    lights
    1.01
     bulb
    1.00
    light
    0.97
    enment
    0.96
     bulbs
    0.96
    lighting
    0.95
    nings
    0.94
    moon
    0.93
    ening
    0.90
     rays
    0.89
    Act Density 0.024%

    No Known Activations