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

    Neuronpedia

    INDEX
    Explanations

    references to financial values such as dollar amounts or percentages

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the article "a" and its frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     organs
    -0.76
    artifacts
    -0.69
     documents
    -0.68
    things
    -0.65
    mot
    -0.65
     fights
    -0.65
     tattoos
    -0.64
     preparations
    -0.64
    eyes
    -0.64
     eg
    -0.63
    POSITIVE LOGITS
     whopping
    1.59
     total
    1.10
     staggering
    1.03
     median
    0.99
     fraction
    0.99
     hefty
    0.98
    verages
    0.97
     ratio
    0.96
     mere
    0.95
     maximum
    0.94
    Act Density 0.254%

    No Known Activations