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

    Neuronpedia

    INDEX
    Explanations

    sources or references

    oai_token-act-pair · gpt-3.5-turbo

    references or citations to sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.76
    ties
    -0.73
     indistinguishable
    -0.73
     heroine
    -0.71
     occasions
    -0.71
     honour
    -0.69
     nostalg
    -0.67
     reintrodu
    -0.66
     challeng
    -0.66
    joice
    -0.66
    POSITIVE LOGITS
     http
    1.05
     Ibid
    1.01
     Retrieved
    1.00
     www
    0.99
     Wikipedia
    0.97
     Cosponsors
    0.96
     Shutterstock
    0.95
     https
    0.93
     Updated
    0.92
     Wikimedia
    0.88
    Act Density 0.066%

    No Known Activations