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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jenkins" as well as references to solar eclipses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PU
    -0.73
     CPC
    -0.71
     tum
    -0.69
     trave
    -0.69
    omach
    -0.68
     rud
    -0.68
     Fare
    -0.67
     leng
    -0.66
    stre
    -0.66
    Rus
    -0.65
    POSITIVE LOGITS
     Jenkins
    3.95
    Jen
    2.12
    jen
    1.64
     eclipse
    1.35
     Eclipse
    1.32
    clipse
    1.18
     Jenner
    1.15
     Django
    1.14
     Ans
    1.10
     Brewer
    1.06
    Act Density 0.021%

    No Known Activations