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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific time periods or phases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imers
    -0.15
     ydk
    -0.15
    dale
    -0.15
    kuk
    -0.15
    å®ĺ
    -0.14
    ÐļТ
    -0.14
    DataExchange
    -0.14
    enburg
    -0.14
    ãĥªãĤ«
    -0.14
    ALSE
    -0.14
    POSITIVE LOGITS
     end
    0.26
     beginning
    0.20
    ught
    0.18
     following
    0.17
     blind
    0.16
    arrass
    0.15
     past
    0.15
     begin
    0.15
     Atlas
    0.15
     e
    0.15
    Act Density 0.125%

    No Known Activations