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

    Neuronpedia

    INDEX
    Explanations

    dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" and its context related to dates or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    channelAvailability
    -0.74
    Reviewer
    -0.68
    Spot
    -0.63
     paran
    -0.62
     differed
    -0.59
    spot
    -0.59
     interacts
    -0.58
     differ
    -0.58
    faces
    -0.57
     wors
    -0.57
    POSITIVE LOGITS
     1979
    1.49
     1981
    1.46
     1974
    1.46
     1976
    1.44
     1992
    1.44
     1982
    1.44
     1978
    1.44
     1990
    1.43
     1971
    1.43
     1993
    1.43
    Act Density 0.156%

    No Known Activations