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

    Neuronpedia

    INDEX
    Explanations

    specific ingredients and their quantities in cooking recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iken
    -0.17
     porr
    -0.16
    rzy
    -0.15
    ानन
    -0.15
    uell
    -0.15
     konkrét
    -0.15
    ibus
    -0.15
     Injector
    -0.14
     wur
    -0.14
     Sutton
    -0.14
    POSITIVE LOGITS
     meth
    0.21
     Je
    0.21
     fen
    0.21
     je
    0.20
     hung
    0.20
     bes
    0.20
     Bes
    0.19
     gram
    0.18
     Hung
    0.18
     card
    0.18
    Act Density 0.046%

    No Known Activations