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

    Neuronpedia

    INDEX
    Explanations

    terms related to theoretical physics and mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auer
    -0.16
    isas
    -0.16
    usta
    -0.15
    getSingleton
    -0.15
    idon
    -0.15
    ahat
    -0.15
    олÑı
    -0.14
    edic
    -0.14
    orna
    -0.14
    ullan
    -0.14
    POSITIVE LOGITS
     theories
    0.26
     gravity
    0.24
     Yang
    0.24
     gauge
    0.22
     theory
    0.21
    Yang
    0.21
    Gravity
    0.21
     ren
    0.20
    theory
    0.20
    Theory
    0.20
    Act Density 0.023%

    No Known Activations