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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and definitions within a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intree
    -0.16
     Stub
    -0.15
    kud
    -0.15
    ump
    -0.15
    osti
    -0.15
    OLA
    -0.14
    logan
    -0.14
    ODE
    -0.14
    æĴĥ
    -0.14
    missive
    -0.14
    POSITIVE LOGITS
    udden
    0.16
    ìĥģìĿĺ
    0.15
    acular
    0.15
     Heaven
    0.14
    enie
    0.14
    ienia
    0.14
     tabel
    0.14
    æł¹
    0.14
    abelle
    0.14
    iren
    0.14
    Act Density 0.211%

    No Known Activations