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

    Neuronpedia

    INDEX
    Explanations

    technical references or code snippets related to programming and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     impactful
    -0.60
    IsContent
    -0.56
     leveraging
    -0.53
    DeclareMath
    -0.53
     
    -0.52
     incentiv
    -0.51
    ️
    -0.51
    劣
    -0.51
     showcased
    -0.51
     ❤️
    -0.50
    POSITIVE LOGITS
     daß
    1.29
     muß
    1.11
     Daß
    1.09
     müßte
    1.08
     idéia
    0.99
     mußte
    0.97
     wußte
    0.89
     mußten
    0.87
    faßt
    0.86
     läßt
    0.86
    Act Density 0.858%

    No Known Activations