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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.85
     minded
    -0.73
     recall
    -0.72
    Advertisement
    -0.72
    .
    -0.70
    rising
    -0.69
    .-
    -0.69
    activity
    -0.68
    ,...
    -0.67
     resent
    -0.67
    POSITIVE LOGITS
     Ibid
    1.50
     Conclusion
    1.22
     Miscellaneous
    1.14
     Various
    1.04
     Closing
    0.98
     Lever
    0.93
     Submit
    0.93
     Introdu
    0.92
     Taxi
    0.92
     Announce
    0.92
    Act Density 0.088%

    No Known Activations