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

    Neuronpedia

    INDEX
    Explanations

    content indicating the continuation of an article with a description of what is below

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing content or sections in an article

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peb
    -0.57
     nomine
    -0.54
     theoret
    -0.54
    ofi
    -0.53
    oult
    -0.53
     metic
    -0.52
     explorers
    -0.50
     bir
    -0.50
     redress
    -0.50
     majesty
    -0.50
    POSITIVE LOGITS
     Below
    1.29
     BELOW
    0.86
     Transcript
    0.70
     Loading
    0.68
     Later
    0.67
     Continued
    0.66
     Subscribe
    0.63
     below
    0.62
    ...]
    0.61
     Continue
    0.60
    Act Density 0.013%

    No Known Activations