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

    Neuronpedia

    INDEX
    Explanations

    references to accumulating or stacking items, particularly in the context of piles or heaps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ABN
    -0.68
     /\.(
    -0.67
     pleaſure
    -0.66
     Majefty
    -0.66
     auffi
    -0.65
     Anſ
    -0.65
    ſelf
    -0.64
     Diſ
    -0.63
    stringValue
    -0.63
    -0.61
    POSITIVE LOGITS
     pile
    4.42
     Pile
    3.63
     piles
    3.63
    pile
    3.52
    Pile
    3.17
     piled
    2.86
     piling
    2.65
     Piles
    2.56
    piles
    2.52
     stack
    2.24
    Act Density 0.138%

    No Known Activations