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

    Neuronpedia

    INDEX
    Explanations

    book citations or references

    oai_token-act-pair · gpt-3.5-turbo

    formal citations and references in a bibliography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.76
     coughing
    -0.65
     lucky
    -0.65
     racing
    -0.65
     shroud
    -0.65
     piping
    -0.63
     Champions
    -0.63
     Ru
    -0.63
     liqu
    -0.63
     deliver
    -0.62
    POSITIVE LOGITS
    âĵĺ
    1.25
    phasis
    0.90
     PubMed
    0.89
     DOI
    0.89
    ibliography
    0.88
    BOOK
    0.88
    References
    0.87
    âĨ
    0.86
    PDF
    0.85
     âĨij
    0.85
    Act Density 0.147%

    No Known Activations