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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and related punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dogged
    -0.87
     seasoned
    -0.82
     persever
    -0.79
     hardened
    -0.79
     bitters
    -0.79
     assured
    -0.79
     whistle
    -0.78
     pacing
    -0.78
     creep
    -0.77
     plateau
    -0.76
    POSITIVE LOGITS
    SELECT
    1.45
    Hello
    1.40
    ./
    1.39
    BuyableInstoreAndOnline
    1.38
    Untitled
    1.32
    hello
    1.27
    foo
    1.27
    abc
    1.26
    ../
    1.26
    default
    1.23
    Act Density 0.050%

    No Known Activations