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

    Neuronpedia

    INDEX
    Explanations

    references to desserts or sweet treats, particularly cakes

    oai_token-act-pair · gpt-3.5-turbo

    references to cake in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.81
    ually
    -0.74
    ENTION
    -0.73
    iveness
    -0.71
    ostics
    -0.70
     Lomb
    -0.67
    OSE
    -0.66
     Cheong
    -0.64
     Fargo
    -0.63
    selves
    -0.62
    POSITIVE LOGITS
    cake
    0.90
    cakes
    0.89
    meal
    0.89
     batter
    0.88
     cake
    0.88
    walk
    0.86
    pillar
    0.83
    hop
    0.80
     cakes
    0.80
     decor
    0.77
    Act Density 0.024%

    No Known Activations