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

    Neuronpedia

    INDEX
    Explanations

    references to an earlier time or date in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Earlier" associated with time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anza
    -0.72
    Baby
    -0.70
     favour
    -0.67
    adr
    -0.63
     otherwise
    -0.61
    76561
    -0.61
    unta
    -0.60
    package
    -0.60
     destiny
    -0.60
    handler
    -0.59
    POSITIVE LOGITS
    noon
    0.89
     recap
    0.78
     editions
    0.75
    nesses
    0.69
     Languages
    0.69
    foundland
    0.68
     versions
    0.68
     evening
    0.67
    iated
    0.65
     Thoughts
    0.64
    Act Density 0.030%

    No Known Activations