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

    Neuronpedia

    INDEX
    Explanations

    phrases related to piles of objects or things

    oai_token-act-pair · gpt-3.5-turbo

    references to accumulations or collections of items, specifically using the term "pile."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     warr
    -0.72
    otiation
    -0.66
    saf
    -0.65
    oral
    -0.65
     livest
    -0.63
     obser
    -0.63
    nton
    -0.62
    abad
    -0.60
    mal
    -0.57
    groupon
    -0.57
    POSITIVE LOGITS
     piles
    1.08
     piling
    0.99
     pile
    0.98
    bags
    0.91
     piled
    0.90
     overflow
    0.72
     clutter
    0.71
    endium
    0.69
    wagon
    0.69
    ickets
    0.69
    Act Density 0.039%

    No Known Activations