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

    Neuronpedia

    INDEX
    Explanations

    temporal references indicating extended durations

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

    duration or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.72
     Carni
    -0.50
    -------
    -0.50
    EAN
    -0.50
    MigrationBuilder
    -0.49
    Rohit
    -0.47
     Италијани
    -0.47
     Rasul
    -0.47
     Lipa
    -0.47
    NDC
    -0.47
    POSITIVE LOGITS
     awhile
    1.68
     lâu
    0.72
    ValueStyle
    0.71
     longtime
    0.55
     longtemps
    0.54
     chví
    0.54
     faſt
    0.52
     occaf
    0.52
    一段时间
    0.52
     idő
    0.51
    Act Density 0.001%

    No Known Activations