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

    Neuronpedia

    INDEX
    Explanations

    references to time durations, specifically years

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

    years ago or later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     împre
    -0.47
     médicale
    -0.45
     alugar
    -0.42
     weiße
    -0.42
     "..\..\
    -0.42
     navideños
    -0.41
     húmedo
    -0.41
     navideño
    -0.40
     informativo
    -0.40
     sikkert
    -0.40
    POSITIVE LOGITS
    两年
    0.54
    数年
    0.52
    几年
    0.52
     year
    0.52
     years
    0.51
    astéroïdes
    0.50
     annually
    0.50
    Year
    0.50
    YEAR
    0.49
     года
    0.48
    Act Density 0.028%

    No Known Activations