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

    Neuronpedia

    INDEX
    Explanations

    references to formal institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overs
    -0.16
    TRACE
    -0.14
     interf
    -0.14
     Stations
    -0.14
    andid
    -0.14
    end
    -0.13
    öff
    -0.13
    ogra
    -0.13
    uta
    -0.13
    arter
    -0.13
    POSITIVE LOGITS
    atrix
    0.17
    .DefaultCellStyle
    0.15
    isters
    0.15
     Alv
    0.15
    hani
    0.14
    xing
    0.14
    /generated
    0.14
    zilla
    0.14
    Ĵáŀ
    0.14
    chwitz
    0.14
    Act Density 0.029%

    No Known Activations