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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, specifically years and durations

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

    "For [number] years" or "since [year]"

    np_acts-logits-general · gemini-2.0-flash

    durations or points in time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quickly
    -0.59
     soon
    -0.59
     recently
    -0.58
     someday
    -0.56
     Sometime
    -0.55
     처
    -0.54
     Wiktionnaire
    -0.54
    今から
    -0.53
     sometime
    -0.53
     damal
    -0.53
    POSITIVE LOGITS
     hinweg
    0.91
     hindurch
    0.71
    Datuak
    0.71
    以來
    0.64
     until
    0.61
    LayoutStyle
    0.59
    UnitTesting
    0.57
    一直
    0.56
    PreferredItem
    0.56
    Until
    0.56
    Act Density 0.237%

    No Known Activations