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

    Neuronpedia

    INDEX
    Explanations

    concepts related to comprehension and understanding of various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mobileqq
    -0.49
    nomin
    -0.47
     favourite
    -0.45
     toppings
    -0.43
    olyb
    -0.43
     paillettes
    -0.43
     bounties
    -0.42
     Dishes
    -0.42
    favourites
    -0.42
    -0.41
    POSITIVE LOGITS
     understanding
    1.64
     Understanding
    1.57
     understand
    1.55
    understanding
    1.49
    Understanding
    1.49
     Understand
    1.45
     understands
    1.41
    understand
    1.41
    Understand
    1.40
     understood
    1.28
    Act Density 0.100%

    No Known Activations