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

    Neuronpedia

    INDEX
    Explanations

    temporal references and time measurements within the text

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

    hour followed by time specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.50
    makeConstraints
    -0.48
     navideños
    -0.44
     transfieras
    -0.43
     Pflanze
    -0.43
     présidentielle
    -0.41
     fotográfica
    -0.40
     navideñas
    -0.39
     sauvage
    -0.38
    $_['
    -0.38
    POSITIVE LOGITS
     hour
    1.13
     Hour
    1.08
    Hour
    1.05
     hours
    1.02
    hour
    1.02
     Hours
    0.99
     HOUR
    0.98
    hours
    0.93
    Hours
    0.93
    HOUR
    0.93
    Act Density 0.170%

    No Known Activations