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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or upcoming changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doch
    -0.16
    Įĵ
    -0.16
     pager
    -0.15
    locs
    -0.15
     Manning
    -0.15
     scram
    -0.14
    dfa
    -0.14
    LEGRO
    -0.14
    eru
    -0.14
    UnitOfWork
    -0.13
    POSITIVE LOGITS
    otts
    0.16
    ustil
    0.15
    ron
    0.15
    ÏĦι
    0.15
    ANJI
    0.15
    ird
    0.14
    ÑĤии
    0.14
    owell
    0.14
    iji
    0.14
    /windows
    0.14
    Act Density 0.043%

    No Known Activations