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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and parameters related to energy performance and flow control equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikk
    -0.17
    nty
    -0.16
    heiro
    -0.14
    orado
    -0.14
     paradigm
    -0.14
    _CAST
    -0.14
    rak
    -0.14
    íıŃ
    -0.14
    thumbs
    -0.13
     scrolls
    -0.13
    POSITIVE LOGITS
     eff
    0.19
    upp
    0.17
     Helm
    0.17
    adir
    0.17
    TOT
    0.17
    eff
    0.17
     obs
    0.16
    ubble
    0.15
    å³°
    0.15
    _{
    0.15
    Act Density 0.162%

    No Known Activations