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

    Neuronpedia

    INDEX
    Explanations

    references to news broadcasts and reporting formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    specific time durations and temporal measurements (hours, minutes, seconds).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     week
    -0.66
     Days
    -0.64
    Days
    -0.62
     yearly
    -0.62
    Week
    -0.62
     days
    -0.61
    Weeks
    -0.60
     Week
    -0.59
     year
    -0.58
     weeks
    -0.58
    POSITIVE LOGITS
     hour
    1.82
     HOUR
    1.57
     Hour
    1.55
    hour
    1.53
    Hour
    1.46
     hours
    1.45
     hourly
    1.41
     minutes
    1.29
     Stunde
    1.29
    hours
    1.24
    Act Density 0.875%

    No Known Activations