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

    Neuronpedia

    INDEX
    Explanations

    concepts related to eigenvalues and matrices in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.07
    659
    -0.07
     Giang
    -0.07
    767
    -0.06
    .dc
    -0.06
     universe
    -0.06
    /logs
    -0.06
    vara
    -0.06
     Yo
    -0.06
    ections
    -0.06
    POSITIVE LOGITS
     eigen
    0.12
     Eigen
    0.11
    Eigen
    0.10
     spectrum
    0.08
     spectral
    0.07
    spect
    0.07
    pectral
    0.07
     spectra
    0.07
    tran
    0.07
    Schedulers
    0.07
    Act Density 0.053%

    No Known Activations