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

    Neuronpedia

    INDEX
    Explanations

    keywords related to different objects or concepts (e.g., kittens, solar panels, grapes, parrots, dogs, eggs, bricks, rockets, coins, Bitcoins, carrots, weapons, items, paintings, animals)

    oai_token-act-pair · gpt-3.5-turbo

    names of various living beings and objects, particularly nouns related to animals, plants, and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¦ãĤ¹
    -0.62
    gee
    -0.61
    rontal
    -0.60
    dds
    -0.60
    nce
    -0.60
     Flavoring
    -0.60
    soType
    -0.60
    ALLY
    -0.59
    ãģĻ
    -0.59
    atalie
    -0.58
    POSITIVE LOGITS
     destined
    1.09
     shipped
    1.09
     themselves
    1.04
    mith
    1.01
     purchased
    0.99
     belonging
    0.97
     sold
    0.97
     harvested
    0.96
     housed
    0.95
     stored
    0.95
    Act Density 0.241%

    No Known Activations