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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical structures and proofs within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.21
     gezocht
    -0.15
    is
    -0.14
    watch
    -0.14
    -
    -0.14
    -v
    -0.14
    l
    -0.14
     Bake
    -0.14
    ________
    -0.14
     &
    -0.13
    POSITIVE LOGITS
    eq
    0.29
     eq
    0.23
     sec
    0.22
    sec
    0.20
    igh
    0.16
    .eq
    0.16
    Ĉ
    0.15
    Sec
    0.15
    SEC
    0.15
     secs
    0.15
    Act Density 0.057%

    No Known Activations