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

    Neuronpedia

    INDEX
    Explanations

    numerical references to centuries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of historical periods or centuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bos
    -0.68
    ãģ¦
    -0.66
    esa
    -0.65
    etsk
    -0.61
    etting
    -0.60
     suscept
    -0.60
    uploads
    -0.59
    storage
    -0.58
     Oblivion
    -0.58
     refunds
    -0.58
    POSITIVE LOGITS
     century
    1.14
    ousand
    1.13
     Amendment
    1.12
     inning
    1.05
     percentile
    1.04
     Century
    1.00
     Circuit
    0.97
    century
    0.97
     Dalai
    0.93
     hour
    0.91
    Act Density 0.035%

    No Known Activations