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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases, specifically referencing durations like "months" or "years."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time, specifically referencing occurrences in the recent past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thence
    -0.68
    adena
    -0.66
    icut
    -0.66
    obal
    -0.64
    UAL
    -0.61
    ater
    -0.61
    obo
    -0.60
    wrapper
    -0.60
    aughter
    -0.59
     ideally
    -0.58
    POSITIVE LOGITS
     months
    1.41
     weeks
    1.40
     years
    1.28
     days
    1.28
     decades
    1.20
     hundred
    1.15
    months
    1.07
     seasons
    1.06
     dozen
    1.05
     paragraphs
    1.05
    Act Density 0.055%

    No Known Activations