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

    Neuronpedia

    INDEX
    Explanations

    references to monetary figures and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and compensation amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patterns
    -0.58
     lately
    -0.57
     Errors
    -0.56
     Yesterday
    -0.55
     fortunately
    -0.53
    ';
    -0.53
    ixties
    -0.53
     wonderfully
    -0.52
     anecd
    -0.52
     Wrong
    -0.52
    POSITIVE LOGITS
     someday
    1.13
     2020
    0.99
     2019
    0.87
     future
    0.85
     preferably
    0.85
     tomorrow
    0.82
     unspecified
    0.81
     next
    0.81
    2020
    0.81
     2024
    0.79
    Act Density 1.749%

    No Known Activations