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

    Neuronpedia

    INDEX
    Explanations

    references to a specific chemical compound or abbreviation, possibly related to health or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to "PA" and its related context, possibly related to a public health or regulatory framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.74
     Alonso
    -0.70
     Conway
    -0.69
    link
    -0.66
    iques
    -0.66
     Axel
    -0.65
     Butterfly
    -0.63
    bolt
    -0.63
    feature
    -0.63
     Loop
    -0.62
    POSITIVE LOGITS
    PA
    1.31
    PET
    1.03
    odcast
    1.01
    ategory
    0.94
    KER
    0.93
    olicy
    0.89
    HAEL
    0.89
    psey
    0.86
    rison
    0.85
    YE
    0.85
    Act Density 0.004%

    No Known Activations