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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time references

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly the phrase "the last x years."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.81
    utor
    -0.73
    $$$$
    -0.70
     nevertheless
    -0.67
    hm
    -0.66
    igans
    -0.66
    ioned
    -0.65
    erers
    -0.62
    iru
    -0.62
     accordingly
    -0.61
    POSITIVE LOGITS
     past
    1.90
     last
    1.50
    past
    1.32
     intervening
    1.30
     recent
    1.17
     years
    1.16
     LAST
    1.06
     Past
    1.06
    Last
    1.05
     previous
    1.04
    Act Density 0.155%

    No Known Activations