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

    Neuronpedia

    INDEX
    Explanations

    dates in a particular format: "Week of [Month Day]"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific routes and their associated week dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enriched
    -0.88
     hyp
    -0.83
     regener
    -0.81
     retard
    -0.80
     revers
    -0.80
     embr
    -0.78
     smugglers
    -0.77
     bil
    -0.77
     brid
    -0.77
     developmental
    -0.77
    POSITIVE LOGITS
    Advertisements
    1.75
    Conclusion
    1.62
    Finally
    1.48
    Additional
    1.46
    Sources
    1.46
    References
    1.44
    Contribut
    1.44
    Trivia
    1.42
    --------------------------------------------------------
    1.41
    Appearances
    1.41
    Act Density 0.152%

    No Known Activations