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

    Neuronpedia

    INDEX
    Explanations

    lamp-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to lamps and lighting devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettings
    -0.76
    ciating
    -0.75
    ãĥį
    -0.73
    OAD
    -0.72
    adelphia
    -0.72
    gerald
    -0.70
    REDACTED
    -0.69
    furt
    -0.69
    llah
    -0.68
    ersion
    -0.68
    POSITIVE LOGITS
     bulbs
    1.28
     bulb
    1.27
     lantern
    0.97
     lamps
    0.96
     candles
    0.94
    orescence
    0.88
     lamp
    0.86
     fluorescent
    0.85
     lights
    0.85
     Lamp
    0.84
    Act Density 0.033%

    No Known Activations