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

    Neuronpedia

    INDEX
    Explanations

    references to stack frames and exceptions in programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deng
    -0.16
    ænd
    -0.15
    phinx
    -0.15
    aktiv
    -0.14
    olini
    -0.14
    ongyang
    -0.14
    izzo
    -0.14
    eldom
    -0.14
    eteria
    -0.13
    äter
    -0.13
    POSITIVE LOGITS
    Shadow
    0.14
    ãĤīãģĦ
    0.14
    (strict
    0.14
    Coding
    0.13
    ft
    0.13
    <typeof
    0.13
    cassert
    0.13
    otope
    0.13
    oning
    0.13
    ArgumentException
    0.12
    Act Density 0.407%

    No Known Activations