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

    Neuronpedia

    INDEX
    Explanations

    words related to sources of illumination

    oai_token-act-pair · gpt-3.5-turbo

    references to "light" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     è£ıè
    -0.83
    stadt
    -0.71
     diplom
    -0.67
    Marg
    -0.67
    employed
    -0.67
    idden
    -0.66
     Surv
    -0.64
    atri
    -0.64
    ournals
    -0.62
    ettings
    -0.62
    POSITIVE LOGITS
     light
    3.63
     Light
    2.51
    light
    2.40
    Light
    2.27
     lights
    2.21
     lighting
    1.93
     lighter
    1.89
    lights
    1.78
     illumination
    1.74
     sunlight
    1.69
    Act Density 0.014%

    No Known Activations