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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÐĹаÑħ
    -0.15
    æĸĹ
    -0.14
    aver
    -0.14
    _NUMERIC
    -0.14
    ãĥ³ãĥIJ
    -0.13
    ạt
    -0.13
    vard
    -0.13
    رÙĪب
    -0.13
    /boot
    -0.13
     ngữ
    -0.13
    POSITIVE LOGITS
     prime
    0.44
    prime
    0.39
     primes
    0.38
     Prime
    0.37
    Prime
    0.35
     factors
    0.31
    _prime
    0.30
     prim
    0.29
     factor
    0.28
    _factors
    0.28
    Act Density 0.232%

    No Known Activations