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

    Neuronpedia

    INDEX
    Explanations

    citations and references from academic journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pun
    -0.14
     pun
    -0.14
     extensions
    -0.14
    aben
    -0.14
     te
    -0.13
    ri
    -0.13
     fim
    -0.13
     Ferm
    -0.13
     WL
    -0.13
    ola
    -0.13
    POSITIVE LOGITS
    emey
    0.16
     Král
    0.15
    isex
    0.14
     ”↵↵
    0.14
    CDATA
    0.14
     offline
    0.13
     @@↵
    0.13
    imuth
    0.13
    úmeros
    0.13
    etus
    0.13
    Act Density 0.006%

    No Known Activations