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

    Neuronpedia

    INDEX
    Explanations

    specific food-related terms and descriptors focusing on ingredients and culinary styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.75
     étoient
    -0.65
     avoient
    -0.64
     quæ
    -0.64
    -0.63
     auroit
    -0.62
     feroit
    -0.61
     faſt
    -0.61
     lèvres
    -0.60
     pouvoit
    -0.59
    POSITIVE LOGITS
     themed
    0.74
     inspired
    0.65
    inspired
    0.65
    flavored
    0.64
    themed
    0.61
     theme
    0.61
     flavored
    0.58
     effect
    0.55
     Inspired
    0.53
     motif
    0.49
    Act Density 0.191%

    No Known Activations