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

    Neuronpedia

    INDEX
    Explanations

    the concept of time relating to recent past events

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal changes or the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pherd
    -0.84
    lees
    -0.82
    olor
    -0.75
    marks
    -0.70
    bos
    -0.66
    obar
    -0.66
    mark
    -0.65
    sure
    -0.65
    then
    -0.65
    wat
    -0.65
    POSITIVE LOGITS
     decade
    1.29
     few
    1.24
     couple
    1.21
     millenn
    1.08
     fortnight
    1.00
     week
    0.95
     month
    0.95
     installment
    0.94
     gasp
    0.94
     weeks
    0.94
    Act Density 0.043%

    No Known Activations