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

    Neuronpedia

    INDEX
    Explanations

    data processing method calls in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    string parsing and manipulation operations in code, especially delimiter/regex-based tokenization and related function calls and symbols.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.65
    ('.');
    -0.55
    __);
    -0.54
     plak
    -0.52
     Persians
    -0.52
     Ouverture
    -0.50
    ("]");
    -0.50
    soort
    -0.49
    __))
    -0.49
    FormTagHelper
    -0.49
    POSITIVE LOGITS
    تقاوى
    0.67
    DllImport
    0.65
     Мексичка
    0.64
    prehensive
    0.62
    SpringRunner
    0.61
    بوابة
    0.61
    Переваги
    0.60
    yntaxException
    0.60
    gsub
    0.60
     meeste
    0.60
    Act Density 0.080%

    No Known Activations