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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.57
     referen
    -0.49
     Moroc
    -0.49
    ãĥ¼ãĥĨ
    -0.47
    idated
    -0.45
    acebook
    -0.43
    allery
    -0.42
    edIn
    -0.41
    ãĤ©
    -0.40
    arij
    -0.39
    POSITIVE LOGITS
    NetMessage
    0.53
    rg
    0.49
     largeDownload
    0.47
    SELECT
    0.43
     DRAGON
    0.43
    cing
    0.42
    serv
    0.39
    othes
    0.39
    posing
    0.38
    taboola
    0.38
    Act Density 1.853%

    No Known Activations