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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and phrases indicating recognition or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungan
    -0.15
    .LoggerFactory
    -0.15
     Ou
    -0.14
    aal
    -0.14
     toolkit
    -0.14
    IBUTES
    -0.14
    康
    -0.14
    .createElement
    -0.14
    ürn
    -0.14
    geist
    -0.14
    POSITIVE LOGITS
     isp
    0.17
    andbox
    0.15
     Chop
    0.14
    ifton
    0.14
     Gins
    0.14
    -bel
    0.14
     Hilton
    0.14
    chop
    0.14
    èĭ
    0.14
    éf
    0.13
    Act Density 0.006%

    No Known Activations