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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their affiliations in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    473
    -0.18
    273
    -0.14
     sao
    -0.14
    474
    -0.14
    ãĥ³ãĤ¿
    -0.13
     McDon
    -0.13
    utsch
    -0.12
    mund
    -0.12
    433
    -0.12
    965
    -0.12
    POSITIVE LOGITS
    _COMMON
    0.15
    ibri
    0.15
    APT
    0.14
     Denied
    0.14
    eka
    0.14
    adle
    0.14
    /Branch
    0.13
     Busty
    0.13
    EMPLARY
    0.13
    veau
    0.13
    Act Density 0.016%

    No Known Activations