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

    Neuronpedia

    INDEX
    Explanations

    reference numbers or academic citations in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Reference" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dav
    -0.71
     Eater
    -0.69
     tear
    -0.68
     simmer
    -0.66
     gri
    -0.66
    atis
    -0.65
     Gaz
    -0.65
     caravan
    -0.64
     sensibilities
    -0.64
    scenes
    -0.61
    POSITIVE LOGITS
    Reference
    3.26
    References
    2.68
    reference
    1.59
     References
    1.50
     refere
    1.21
     Reference
    1.17
    Conclusion
    1.11
    ا
    1.00
    Reviewed
    0.97
    ibliography
    0.97
    Act Density 0.039%

    No Known Activations