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

    Neuronpedia

    INDEX
    Explanations

    technical concepts related to equations and mathematical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahir
    -0.15
    lw
    -0.15
     Miche
    -0.14
    openh
    -0.14
    лег
    -0.14
    acent
    -0.14
    gid
    -0.14
     yard
    -0.14
    iped
    -0.14
    obili
    -0.14
    POSITIVE LOGITS
     eigen
    0.19
    inalg
    0.19
     Eigen
    0.18
    Orth
    0.17
     Linear
    0.17
    getRow
    0.17
     Orth
    0.16
     norm
    0.16
     matrix
    0.16
    orth
    0.16
    Act Density 0.085%

    No Known Activations