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

    Neuronpedia

    INDEX
    Explanations

    mentions of pairs of items or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to pairs of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.87
    UGE
    -0.71
    ADRA
    -0.71
    Interstitial
    -0.71
     Causes
    -0.69
    inez
    -0.69
    INA
    -0.69
    emetery
    -0.68
     Occupations
    -0.65
    ICLE
    -0.62
    POSITIVE LOGITS
    pair
    0.97
    ings
    0.96
    wise
    0.92
    rings
    0.90
    ably
    0.89
    horn
    0.81
     mates
    0.81
    lihood
    0.80
     pair
    0.78
     paired
    0.77
    Act Density 0.023%

    No Known Activations