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

    Neuronpedia

    INDEX
    Explanations

    references to durations and periods of time in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    years
    -0.21
     Years
    -0.20
    -years
    -0.20
    Years
    -0.19
     yrs
    -0.18
     years
    -0.18
     années
    -0.17
    å¹´
    -0.17
    year
    -0.17
     decades
    -0.17
    POSITIVE LOGITS
     weeks
    0.38
     days
    0.33
    weeks
    0.30
     fortn
    0.28
     week
    0.28
     Weeks
    0.28
     DAYS
    0.27
     nearly
    0.26
     two
    0.26
     almost
    0.25
    Act Density 0.091%

    No Known Activations