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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atham
    -0.15
    иком
    -0.15
    woord
    -0.15
    memberof
    -0.15
    รร
    -0.14
    pell
    -0.14
    iese
    -0.14
     preferredStyle
    -0.14
    afia
    -0.13
    ellig
    -0.13
    POSITIVE LOGITS
    .bundle
    0.14
     getChild
    0.14
     Vent
    0.14
     irre
    0.13
    æĺ¥
    0.13
     ponder
    0.13
     Sad
    0.13
     Rog
    0.13
     irres
    0.13
    koli
    0.13
    Act Density 0.006%

    No Known Activations