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

    Neuronpedia

    INDEX
    Explanations

    references to specific types of food and dietary choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erty
    -0.17
    kova
    -0.17
    ively
    -0.17
    artial
    -0.16
    urn
    -0.16
    esc
    -0.15
    ovice
    -0.15
    ught
    -0.15
    AM
    -0.15
    urch
    -0.15
    POSITIVE LOGITS
    bone
    0.22
    pool
    0.20
    bohydr
    0.19
    rying
    0.18
    riages
    0.18
    ibbean
    0.17
    ilage
    0.17
    oten
    0.17
    thers
    0.17
    -Semit
    0.17
    Act Density 0.053%

    No Known Activations