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

    Neuronpedia

    INDEX
    Explanations

    structured references and citations in academic documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fect
    -0.17
    pheres
    -0.16
    elper
    -0.16
    neys
    -0.15
    егоÑĢ
    -0.15
    клад
    -0.15
    418
    -0.15
    elen
    -0.14
    elyn
    -0.14
    encia
    -0.14
    POSITIVE LOGITS
    arkin
    0.19
    iei
    0.16
    tee
    0.16
    zag
    0.16
    æį·
    0.15
    hir
    0.14
    طة
    0.14
     Gos
    0.14
    xiv
    0.14
    cheon
    0.13
    Act Density 0.006%

    No Known Activations