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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADVERTISEMENT
    -0.15
     seins
    -0.14
     compens
    -0.14
    jours
    -0.14
     SetLastError
    -0.14
    楽
    -0.14
    AGON
    -0.14
    estone
    -0.14
    令
    -0.14
     crossorigin
    -0.14
    POSITIVE LOGITS
    ัย
    0.17
    ãĤ¶ãĥ¼
    0.15
     Kos
    0.15
    rodu
    0.15
     Tie
    0.15
    áb
    0.14
    rede
    0.14
    upp
    0.14
    raction
    0.14
    cak
    0.14
    Act Density 0.166%

    No Known Activations