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

    Neuronpedia

    INDEX
    Explanations

    dates or years preceded by "in"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" followed by associated historical context or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    channelAvailability
    -0.90
     likened
    -0.71
     therein
    -0.63
     prosec
    -0.62
     weighs
    -0.62
     distances
    -0.61
     compared
    -0.60
     accounted
    -0.60
     INCLUD
    -0.59
     ster
    -0.59
    POSITIVE LOGITS
     2005
    1.39
     1979
    1.39
     1981
    1.39
     1988
    1.38
     2009
    1.38
     1991
    1.38
     1978
    1.37
     2004
    1.37
     2006
    1.37
     1982
    1.37
    Act Density 0.271%

    No Known Activations