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

    Neuronpedia

    INDEX
    Explanations

    keywords related to people, places, and events

    oai_token-act-pair · gpt-3.5-turbo

    references to art or artistic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.75
     burden
    -0.65
     cumbers
    -0.65
     ker
    -0.64
     iod
    -0.63
     dime
    -0.62
     snowy
    -0.62
     chloride
    -0.61
    ascus
    -0.60
    ELD
    -0.59
    POSITIVE LOGITS
    ifact
    1.20
    illery
    1.14
    icles
    1.05
    heid
    1.04
    ificial
    1.01
    esian
    1.00
    isans
    0.99
    ooth
    0.98
    oon
    0.96
    ICLE
    0.95
    Act Density 0.019%

    No Known Activations