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

    Neuronpedia

    INDEX
    Explanations

    references to milk and dairy products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sembles
    -0.16
    ihar
    -0.14
    een
    -0.14
    ad
    -0.14
    nels
    -0.14
    λλη
    -0.14
    Æł
    -0.14
    yth
    -0.13
    çıŃ
    -0.13
    ipse
    -0.13
    POSITIVE LOGITS
    shake
    0.32
    maid
    0.29
     milk
    0.26
    maids
    0.26
     Milk
    0.23
    aukee
    0.22
     MIL
    0.20
     mil
    0.20
     lact
    0.20
     dairy
    0.19
    Act Density 0.010%

    No Known Activations