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

    Neuronpedia

    INDEX
    Explanations

    references to coding or document formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ijken
    -0.17
    lak
    -0.16
    rien
    -0.15
    tram
    -0.14
    ##_
    -0.14
     Silver
    -0.14
    sitemap
    -0.13
    Ñĵ
    -0.13
    hir
    -0.13
     terr
    -0.13
    POSITIVE LOGITS
    utex
    0.21
    =pd
    0.19
    utf
    0.17
    UTF
    0.17
    .cls
    0.17
     paper
    0.16
    -paper
    0.16
    è«ĸ
    0.16
    article
    0.16
    _beam
    0.16
    Act Density 0.036%

    No Known Activations