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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and formatting within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.16
    isters
    -0.16
    IOD
    -0.15
    ær
    -0.14
    iest
    -0.14
    sen
    -0.14
    Cached
    -0.14
    esen
    -0.14
    SES
    -0.13
    nesc
    -0.13
    POSITIVE LOGITS
    emme
    0.15
    owler
    0.15
    cco
    0.15
     Venture
    0.14
    atat
    0.14
    ÙĬÙģØ©
    0.14
    urus
    0.13
     {?>↵
    0.13
     tol
    0.13
    coder
    0.13
    Act Density 0.102%

    No Known Activations