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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases and repetition patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isters
    -0.16
    rell
    -0.15
    ippo
    -0.15
     CDDL
    -0.15
    ria
    -0.15
    readcr
    -0.15
    istration
    -0.14
    ui
    -0.14
    urent
    -0.14
    yle
    -0.14
    POSITIVE LOGITS
    à¥įध
    0.16
    缤
    0.14
    égor
    0.14
     Dut
    0.14
    มาย
    0.14
    mav
    0.13
    CSR
    0.13
    @mail
    0.13
     duties
    0.13
     Böl
    0.12
    Act Density 0.018%

    No Known Activations