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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifu
    -0.16
    unker
    -0.15
    stu
    -0.14
    Ĭ
    -0.14
    .Options
    -0.14
    786
    -0.14
    ogenerated
    -0.13
    rej
    -0.13
     wel
    -0.13
    rsp
    -0.13
    POSITIVE LOGITS
    InSection
    0.17
    .results
    0.16
     results
    0.15
    .Restr
    0.15
    먼
    0.15
    .simps
    0.15
     outline
    0.15
    mazon
    0.15
     Truy
    0.15
     Section
    0.14
    Act Density 0.065%

    No Known Activations