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

    Neuronpedia

    INDEX
    Explanations

    references to spans of time, specifically "years"

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, particularly in years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.90
    eus
    -0.78
    iqu
    -0.75
    anus
    -0.73
    ess
    -0.72
    icum
    -0.71
    hod
    -0.70
    achus
    -0.67
    perse
    -0.66
     subp
    -0.66
    POSITIVE LOGITS
     ago
    1.34
     Ago
    1.03
     olds
    0.95
     old
    0.84
     hindsight
    0.80
     nostalg
    0.78
     apiece
    0.73
     overdue
    0.73
     Anniversary
    0.72
     anniversary
    0.72
    Act Density 0.102%

    No Known Activations