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

    Neuronpedia

    INDEX
    Explanations

    concepts and reflections about the nature of reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    echa
    -0.19
     éĥ
    -0.17
    ikon
    -0.16
    asma
    -0.15
    ewan
    -0.15
    KHR
    -0.15
    amat
    -0.14
    edback
    -0.14
    íĿ¬
    -0.14
    æº
    -0.14
    POSITIVE LOGITS
     appears
    0.16
     eins
    0.16
     leaving
    0.15
    illet
    0.15
     dece
    0.15
    Äįin
    0.15
     Lug
    0.15
     appear
    0.15
    abal
    0.15
    shaw
    0.14
    Act Density 0.080%

    No Known Activations