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

    Neuronpedia

    INDEX
    Explanations

    references to gauge theory concepts and terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    st
    -0.71
    t
    -0.71
    al
    -0.69
    l
    -0.66
    enerys
    -0.66
    n
    -0.64
    a
    -0.63
    stine
    -0.63
     ritard
    -0.62
    most
    -0.61
    POSITIVE LOGITS
     Gauge
    1.77
     gauges
    1.66
     gauge
    1.64
    Gauge
    1.60
    gauge
    1.53
    auge
    1.27
     Gau
    1.27
    Gau
    1.26
     Gage
    1.20
    DockStyle
    1.16
    Act Density 0.016%

    No Known Activations