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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions within a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¹ãĤ«
    -0.17
    ling
    -0.17
     Norris
    -0.16
    iris
    -0.16
    aç
    -0.15
    765
    -0.15
    iel
    -0.15
    UnitTest
    -0.14
    aje
    -0.14
    κÎŃ
    -0.14
    POSITIVE LOGITS
    tainment
    0.15
    rouch
    0.15
    sob
    0.15
    okino
    0.15
    _COMPAT
    0.14
     lam
    0.14
    меÑĢик
    0.14
    ritz
    0.14
    icer
    0.14
    anagan
    0.13
    Act Density 0.477%

    No Known Activations