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

    Neuronpedia

    INDEX
    Explanations

    dates and other time-related information

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and significant numerical references within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rosenberg
    -0.78
     Schwartz
    -0.77
     tox
    -0.76
    zbollah
    -0.75
     DP
    -0.75
    resso
    -0.73
     Cort
    -0.73
     billboard
    -0.70
     PW
    -0.70
     Trib
    -0.70
    POSITIVE LOGITS
    18
    1.79
     18
    1.68
     1886
    1.24
     1888
    1.23
    19
    1.21
     1840
    1.21
     1889
    1.20
     1860
    1.19
     1850
    1.18
     1830
    1.15
    Act Density 0.144%

    No Known Activations