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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "block" in instances such as "blocked," "unblock," or "blockchain."

    oai_token-act-pair · gpt-3.5-turbo

    references to "block" and its variations, particularly in relation to blockchain technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.71
     reluct
    -0.69
    rouse
    -0.65
    ufact
    -0.65
     lowly
    -0.62
    itars
    -0.61
     Bie
    -0.61
     dishon
    -0.61
     swear
    -0.60
     rugged
    -0.60
    POSITIVE LOGITS
    block
    1.28
    buster
    1.13
    quote
    1.09
    busters
    1.03
    chain
    1.03
    blocks
    1.00
    chains
    0.92
    aby
    0.87
    yard
    0.85
    tree
    0.82
    Act Density 0.004%

    No Known Activations