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

    Neuronpedia

    INDEX
    Explanations

    questions or prompts with a question mark at the end

    oai_token-act-pair · gpt-3.5-turbo

    questions marks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikuman
    -0.87
     referen
    -0.85
     corrid
    -0.78
     subur
    -0.73
     carbohyd
    -0.73
     earthqu
    -0.71
     transition
    -0.70
     nodd
    -0.69
     srf
    -0.67
     unintention
    -0.67
    POSITIVE LOGITS
     Does
    1.56
     Answer
    1.45
     Are
    1.44
     Would
    1.44
     Surely
    1.43
     Should
    1.42
     How
    1.41
     Could
    1.38
     Wouldn
    1.37
     What
    1.36
    Act Density 0.149%

    No Known Activations