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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'light' or related terms such as 'Lights', often within a spiritual or metaphorical context

    oai_token-act-pair · gpt-3.5-turbo

    references to "Light" and its associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.86
    PsyNetMessage
    -0.82
    llah
    -0.72
    çīĪ
    -0.72
    ä½ľ
    -0.68
    CVE
    -0.68
    ODUCT
    -0.68
     Boko
    -0.67
    ersion
    -0.67
    ettings
    -0.66
    POSITIVE LOGITS
    light
    1.06
    bringer
    1.00
     Light
    1.00
    hearted
    0.97
    lights
    0.95
     bulb
    0.92
    weight
    0.90
    aber
    0.90
    ening
    0.89
    Light
    0.89
    Act Density 0.009%

    No Known Activations