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

    Neuronpedia

    INDEX
    Explanations

    references to history, specifically historical events and details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    details
    -0.79
    )))
    -0.77
    CONCLUS
    -0.75
    Conclusion
    -0.73
    $$$$
    -0.72
    atories
    -0.72
    ptoms
    -0.69
    taboola
    -0.69
    isance
    -0.69
     )))
    -0.68
    POSITIVE LOGITS
     childhood
    1.31
     infancy
    1.08
     adolescence
    1.07
     1971
    0.96
     1979
    0.94
     1969
    0.94
     upbringing
    0.93
     1980
    0.93
     1989
    0.91
     1968
    0.91
    Act Density 0.957%

    No Known Activations