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

    Neuronpedia

    INDEX
    Explanations

    cooking-related actions or utensils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chase
    -0.16
    enerative
    -0.15
     Lâm
    -0.14
     ÄIJo
    -0.14
    artic
    -0.13
     Desmond
    -0.13
    uze
    -0.13
     chilled
    -0.13
     emb
    -0.13
    jos
    -0.13
    POSITIVE LOGITS
     cooking
    0.30
     Cooking
    0.24
     cook
    0.24
     stove
    0.23
    Cook
    0.22
     heat
    0.22
    çħ
    0.22
     cooker
    0.20
     flames
    0.20
     frying
    0.20
    Act Density 0.202%

    No Known Activations