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

    Neuronpedia

    INDEX
    Explanations

    words related to light sources

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "light" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.85
    sonian
    -0.81
    ilon
    -0.78
    ordan
    -0.74
    CVE
    -0.72
    icter
    -0.72
    SU
    -0.72
    keye
    -0.71
    ettings
    -0.70
    keyes
    -0.69
    POSITIVE LOGITS
    enment
    1.27
    lights
    1.15
    weights
    0.87
    light
    0.84
     bulb
    0.82
    ening
    0.80
    bul
    0.80
    ened
    0.79
    ning
    0.79
    nings
    0.78
    Act Density 0.013%

    No Known Activations