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

    Neuronpedia

    INDEX
    Explanations

    time-related words such as "year", "month", and "week"

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations, specifically months and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.75
    inav
    -0.74
    ashtra
    -0.74
    casts
    -0.73
    hett
    -0.70
    uctions
    -0.68
    jri
    -0.67
     corridors
    -0.66
    ãĤ¢ãĥ«
    -0.66
    ktop
    -0.65
    POSITIVE LOGITS
     ago
    1.14
     Ago
    1.09
    long
    0.88
    dozen
    0.83
    night
    0.78
    iversary
    0.74
    glass
    0.72
     apiece
    0.72
    nd
    0.70
    arro
    0.68
    Act Density 0.101%

    No Known Activations