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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical piles of objects or substances

    oai_token-act-pair · gpt-3.5-turbo

    references to "pile" or "piles" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     obser
    -0.68
     warr
    -0.66
    oral
    -0.66
     livest
    -0.65
    abad
    -0.63
    otiation
    -0.62
    hips
    -0.62
    metic
    -0.60
    cffffcc
    -0.58
     Pione
    -0.58
    POSITIVE LOGITS
     piles
    1.04
     piling
    1.01
     pile
    1.00
    bags
    0.95
     piled
    0.84
    endium
    0.77
    wagon
    0.76
     heap
    0.76
    bag
    0.75
    aging
    0.73
    Act Density 0.017%

    No Known Activations