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

    Neuronpedia

    INDEX
    Explanations

    code snippets implementing string manipulation and printing

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and JSON-like structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nunes
    -0.73
     Hoo
    -0.71
     RC
    -0.68
     Kear
    -0.66
    -0.66
     Kin
    -0.65
     TTL
    -0.65
     incidentally
    -0.64
     Hai
    -0.62
     Sax
    -0.62
    POSITIVE LOGITS
    catentry
    0.98
    english
    0.95
    wcsstore
    0.92
    Hello
    0.91
    hello
    0.90
    dogs
    0.88
    ../
    0.87
    tnc
    0.86
    \/\/
    0.85
    Grand
    0.83
    Act Density 0.033%

    No Known Activations