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

    Neuronpedia

    INDEX
    Explanations

    culinary references and specific food ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yclic
    -0.15
    ystate
    -0.15
    croll
    -0.15
    esson
    -0.14
     Mét
    -0.14
     Steele
    -0.14
    riage
    -0.14
     paris
    -0.14
     Filter
    -0.13
    adow
    -0.13
    POSITIVE LOGITS
     peppers
    0.38
     Caps
    0.35
     chili
    0.35
     chill
    0.32
     pepper
    0.32
     hab
    0.31
    Caps
    0.30
     caps
    0.29
     hotter
    0.29
    caps
    0.28
    Act Density 0.075%

    No Known Activations