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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and references to academic sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amp
    -0.15
    erson
    -0.15
    affen
    -0.14
     trá»Ŀi
    -0.14
    ente
    -0.14
    -0.14
    /Page
    -0.14
    plates
    -0.13
    475
    -0.13
    forc
    -0.13
    POSITIVE LOGITS
    ignet
    0.22
    #ac
    0.16
    ÙĪÙĩ
    0.15
    æ¡£
    0.15
    hol
    0.15
    éĻµ
    0.15
    otic
    0.14
    iler
    0.14
    ÙĬÙĨÙĩ
    0.14
    omers
    0.14
    Act Density 0.012%

    No Known Activations