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

    Neuronpedia

    INDEX
    Explanations

    references to durations of time or working hours

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

    time in hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itic
    -0.41
     sticky
    -0.40
    ieder
    -0.39
     wildest
    -0.38
     Davidson
    -0.36
    siapkan
    -0.36
    ی
    -0.36
    jface
    -0.35
    faßt
    -0.35
     kırmızı
    -0.35
    POSITIVE LOGITS
     hours
    1.98
     Hours
    1.97
    hours
    1.88
    Hours
    1.88
     Hour
    1.74
    Hour
    1.73
     HOURS
    1.71
    HOURS
    1.63
     hour
    1.62
    hour
    1.61
    Act Density 0.013%

    No Known Activations