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

    Neuronpedia

    INDEX
    Explanations

    collections of items or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to collections or groups of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pher
    -0.83
     unden
    -0.67
    yl
    -0.67
    mic
    -0.64
    forth
    -0.63
    runner
    -0.61
    twitch
    -0.60
    acl
    -0.60
    generic
    -0.59
    abad
    -0.58
    POSITIVE LOGITS
    collection
    0.96
     collection
    0.93
     collections
    0.88
     Collection
    0.88
    ĸļ
    0.87
    uably
    0.85
     Collections
    0.80
    icles
    0.79
    ieu
    0.77
    naire
    0.75
    Act Density 0.020%

    No Known Activations