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

    Neuronpedia

    INDEX
    Explanations

    keywords related to the contextual information of the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "context."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STON
    -0.75
    riage
    -0.73
    aah
    -0.71
    dinand
    -0.71
    deen
    -0.70
    vals
    -0.70
    itting
    -0.67
    itte
    -0.66
    thing
    -0.66
    DAQ
    -0.65
    POSITIVE LOGITS
     context
    1.03
     contexts
    0.89
     Context
    0.87
    uality
    0.82
    ually
    0.81
    ual
    0.79
     sensitivity
    0.72
     contextual
    0.72
    raints
    0.71
    Impl
    0.66
    Act Density 0.015%

    No Known Activations