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

    Neuronpedia

    INDEX
    Explanations

    references to specific cooking techniques or recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fruits
    -0.17
    lew
    -0.16
    fruit
    -0.16
     fruit
    -0.15
    acen
    -0.15
     carrot
    -0.14
    iÄį
    -0.14
    acom
    -0.14
     trench
    -0.14
     sac
    -0.14
    POSITIVE LOGITS
     Bought
    0.21
     Trader
    0.18
     buys
    0.18
     frozen
    0.18
     canned
    0.18
     store
    0.17
     purchased
    0.17
     bought
    0.17
    Reserved
    0.17
     drained
    0.17
    Act Density 0.061%

    No Known Activations