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

    Neuronpedia

    INDEX
    Explanations

    languages and names, particularly featuring the words "Davis" and "Le"

    oai_token-act-pair · gpt-3.5-turbo

    names and identifiers of people, places, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reincarn
    -0.65
    ĨĴ
    -0.64
    Condition
    -0.61
    Versions
    -0.61
    CLASSIFIED
    -0.61
    Anything
    -0.60
    catentry
    -0.60
     INCLUD
    -0.58
    abul
    -0.58
     Leban
    -0.56
    POSITIVE LOGITS
    heed
    0.88
    gow
    0.81
    ibrary
    0.79
    ength
    0.73
    monds
    0.72
    udic
    0.71
    oyd
    0.71
    ounge
    0.71
    tarians
    0.71
    itzer
    0.70
    Act Density 0.658%

    No Known Activations