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

    Neuronpedia

    INDEX
    Explanations

    JavaScript function invocations

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and brackets in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kindly
    -0.69
     whip
    -0.68
     handc
    -0.68
     clinch
    -0.66
     dece
    -0.66
     Anglic
    -0.65
     bruising
    -0.65
     electr
    -0.64
     spirits
    -0.62
     eyel
    -0.62
    POSITIVE LOGITS
    ...)
    1.08
    ())
    1.03
    std
    1.00
    BOOK
    0.98
    ctx
    0.98
    src
    0.97
    context
    0.96
    failed
    0.95
    username
    0.94
    input
    0.94
    Act Density 0.025%

    No Known Activations