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

    Neuronpedia

    INDEX
    Explanations

    time-related references, particularly mentioning specific time periods, such as years

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically relating to the last several years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollow
    -0.74
    oola
    -0.73
    aband
    -0.69
    nel
    -0.64
    amber
    -0.64
    ancel
    -0.63
    obs
    -0.62
    iform
    -0.62
    ingen
    -0.61
    olor
    -0.61
    POSITIVE LOGITS
     decade
    1.22
     month
    1.04
     week
    1.01
     gasp
    0.96
     year
    0.94
     installment
    0.94
     millennium
    0.93
     few
    0.91
    ebin
    0.90
     century
    0.89
    Act Density 0.038%

    No Known Activations