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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to code and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    quoted strings and apostrophes in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arius
    -0.68
    avorite
    -0.65
     surpr
    -0.64
     dipping
    -0.64
    ierre
    -0.62
     matter
    -0.60
     Canaver
    -0.60
    ensibly
    -0.59
     dogged
    -0.58
    riks
    -0.58
    POSITIVE LOGITS
    ./
    1.04
    BuyableInstoreAndOnline
    1.00
    wcsstore
    0.97
    SELECT
    0.89
    Usage
    0.88
    Hello
    0.84
    Untitled
    0.83
    ../
    0.81
    hello
    0.81
    foo
    0.81
    Act Density 0.027%

    No Known Activations