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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the flow of something

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of flow, including goods, information, and traffic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avez
    -0.70
    andals
    -0.64
     scratched
    -0.64
     à¨
    -0.62
    Ü
    -0.62
     SAY
    -0.61
    ãĥ¯ãĥ³
    -0.61
    ifications
    -0.61
     Bav
    -0.60
     citiz
    -0.58
    POSITIVE LOGITS
    chart
    1.37
    flow
    1.01
     flowing
    0.94
    flows
    0.93
     flows
    0.90
    sheet
    0.89
    ered
    0.87
    stream
    0.85
    efully
    0.85
    sheets
    0.85
    Act Density 0.041%

    No Known Activations