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

    Neuronpedia

    INDEX
    Explanations

    references to food preferences and eating experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cinnamon
    -0.08
     chocol
    -0.07
     cocoa
    -0.07
    664
    -0.07
    -cookie
    -0.07
    Chocolate
    -0.07
     bisc
    -0.07
     oat
    -0.07
    bread
    -0.07
     bánh
    -0.07
    POSITIVE LOGITS
     vegetables
    0.16
     greens
    0.15
     veggies
    0.14
     Greens
    0.13
    greens
    0.12
     vegetable
    0.11
     green
    0.11
     Brussels
    0.11
     cruc
    0.10
     VE
    0.10
    Act Density 0.178%

    No Known Activations