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

    Neuronpedia

    INDEX
    Explanations

    endings of sentences and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SKU
    -0.15
    .unpack
    -0.14
    Translation
    -0.14
    DataURL
    -0.14
    icha
    -0.13
    .dict
    -0.13
    rolls
    -0.13
    CRYPT
    -0.13
    thon
    -0.13
    translation
    -0.13
    POSITIVE LOGITS
    Conclusion
    0.25
     Above
    0.25
    Above
    0.24
    以ä¸Ĭ
    0.23
     above
    0.23
    Hopefully
    0.23
     Conclusion
    0.23
     conclusion
    0.22
     concludes
    0.21
    ONUS
    0.21
    Act Density 0.057%

    No Known Activations