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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to scientific equations and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ActiveRecord
    -0.43
    ürzen
    -0.39
    />";
    -0.39
    engeance
    -0.38
    ytä
    -0.38
    ifrance
    -0.37
    "]="
    -0.37
    voja
    -0.36
    Історія
    -0.36
     gudang
    -0.35
    POSITIVE LOGITS
     moments
    0.65
     spectrum
    0.63
     spectra
    0.61
     Moments
    0.57
     expectation
    0.56
     eigenvalues
    0.55
    moments
    0.54
     Spectrum
    0.53
     Green
    0.53
    Spectrum
    0.51
    Act Density 2.482%

    No Known Activations