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

    Neuronpedia

    INDEX
    Explanations

    concepts related to stability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.15
    elson
    -0.15
    anut
    -0.15
     киÑģл
    -0.15
    eren
    -0.15
    åĢij
    -0.14
    DonaldTrump
    -0.14
    elsing
    -0.14
    IODevice
    -0.14
     billig
    -0.14
    POSITIVE LOGITS
    kker
    0.17
    andalone
    0.15
    urdy
    0.14
    Ñīи
    0.14
    uart
    0.14
    urt
    0.14
    -rest
    0.13
    bjerg
    0.13
    issor
    0.13
    ude
    0.13
    Act Density 0.023%

    No Known Activations