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

    Neuronpedia

    INDEX
    Explanations

    words related to containers, especially buckets

    oai_token-act-pair · gpt-3.5-turbo

    references to "bucket" as a concept, often in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ournal
    -0.83
    enegger
    -0.80
    uality
    -0.73
    GGGGGGGG
    -0.69
     Kham
    -0.67
    eanor
    -0.66
    agogue
    -0.64
    eca
    -0.64
    âĸ¬
    -0.63
    onduct
    -0.62
    POSITIVE LOGITS
    loads
    0.91
    chest
    0.88
     Rapids
    0.85
     bucket
    0.84
    hatt
    0.82
     buckets
    0.79
     brigade
    0.77
     Bucket
    0.76
    pipe
    0.76
    mates
    0.74
    Act Density 0.043%

    No Known Activations