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

    Neuronpedia

    INDEX
    Explanations

    references to bread and related culinary terms

    oai_token-act-pair · gpt-3.5-turbo

    references to bread

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uate
    -0.85
     Cheong
    -0.70
    NRS
    -0.69
    Population
    -0.69
    uated
    -0.68
    uating
    -0.68
    å°Ĩ
    -0.68
    ARP
    -0.67
    ORT
    -0.67
    UTION
    -0.67
    POSITIVE LOGITS
    fruit
    1.11
     dough
    1.01
     bread
    1.01
    sticks
    1.00
     pudding
    1.00
    winner
    0.99
     Seym
    0.99
    grain
    0.95
    nut
    0.94
    cr
    0.92
    Act Density 0.011%

    No Known Activations