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

    Neuronpedia

    INDEX
    Explanations

    grace

    np_max-act · gemini-2.0-flash

    terms associated with negative traits or behaviors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Poll
    -0.08
    &#
    -0.07
     reported
    -0.07
    otti
    -0.07
     POLL
    -0.06
    Poll
    -0.06
     yurt
    -0.06
     Overnight
    -0.06
     đứng
    -0.06
     ebay
    -0.06
    POSITIVE LOGITS
     Grace
    0.15
     grace
    0.13
    Grace
    0.13
     Brace
    0.10
     gracious
    0.10
    rice
    0.09
     graceful
    0.09
     grâce
    0.08
    aces
    0.08
     Rash
    0.08
    Act Density 0.009%

    No Known Activations