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

    Neuronpedia

    INDEX
    Explanations

    time periods represented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and names related to statistics or historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bray
    -0.97
     Shank
    -0.89
    Bir
    -0.81
    arth
    -0.78
     Brah
    -0.75
     Hem
    -0.72
    roth
    -0.72
     Bai
    -0.72
     lash
    -0.70
     Hound
    -0.69
    POSITIVE LOGITS
     1998
    1.28
     1999
    1.24
    98
    1.20
    1998
    1.20
     98
    1.18
     1997
    1.16
    1999
    1.15
     2000
    1.13
     1996
    1.08
    97
    1.07
    Act Density 0.192%

    No Known Activations