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

    Neuronpedia

    INDEX
    Explanations

    dates of the week

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days of the week

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     territory
    -0.74
     2000
    -0.72
     multiple
    -0.71
     bi
    -0.71
     application
    -0.70
     origin
    -0.69
     control
    -0.69
     U
    -0.68
     era
    -0.66
     2005
    -0.66
    POSITIVE LOGITS
    Tuesday
    2.62
    Wednesday
    2.60
    Thursday
    2.55
    Monday
    2.40
    Friday
    2.38
    Sunday
    2.34
    Saturday
    2.31
    Tomorrow
    1.37
    aturday
    1.34
    Yesterday
    1.28
    Act Density 0.013%

    No Known Activations