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

    Neuronpedia

    INDEX
    Explanations

    structured data representation, particularly in programming or database contexts

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

    structured, non-prose text (code/math/data-style listings) characterized by symbols, delimiters, indices, and repetitive punctuation

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
     تضيفلها
    -1.13
     bezeichneter
    -1.03
    Datuak
    -0.98
     مشين
    -0.97
    Diweddarwch
    -0.95
    الإنجليزية
    -0.95
    ISupport
    -0.94
     tartalomajánló
    -0.94
    parsedMessage
    -0.92
    __':
    -0.88
    POSITIVE LOGITS
    Viitteet
    0.43
    of
    0.39
    O
    0.38
    as
    0.35
    to
    0.34
    ini
    0.34
     Adam
    0.34
    综
    0.33
     silla
    0.33
    at
    0.33
    Act Density 1.690%

    No Known Activations