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

    Neuronpedia

    INDEX
    Explanations

    references to a bowl and its contents or related instructions in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estimés
    -0.88
    a
    -0.78
     Ge
    -0.58
    انت
    -0.57
     sự
    -0.56
     hű
    -0.55
     lin
    -0.55
    ţa
    -0.55
    jona
    -0.54
    baran
    -0.54
    POSITIVE LOGITS
     bowl
    3.58
     Bowl
    3.36
     bowls
    3.10
    bowl
    3.10
    Bowl
    3.09
     Bowls
    2.79
     BOW
    2.48
     bowled
    2.04
    BOW
    1.91
    Bow
    1.76
    Act Density 0.056%

    No Known Activations