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

    Neuronpedia

    INDEX
    Explanations

    names or terms starting with the letter "C" that often include a person's name or a brand

    oai_token-act-pair · gpt-3.5-turbo

    specific tokens related to a particular category or context, indicated by the pattern of activations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chero
    -0.68
     Tinder
    -0.67
     GOODMAN
    -0.66
    uyomi
    -0.64
     Eston
    -0.62
     Yamaha
    -0.62
     Wrestle
    -0.61
     props
    -0.60
     opening
    -0.60
     Rebels
    -0.59
    POSITIVE LOGITS
    overed
    1.35
    URRENT
    1.31
    esar
    1.29
    rossover
    1.27
    ottage
    1.27
    auldron
    1.25
    actus
    1.24
    abbage
    1.23
    rouch
    1.22
    ursor
    1.21
    Act Density 0.047%

    No Known Activations