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

    Neuronpedia

    INDEX
    Explanations

    numbers representing specific ages within text

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 18 and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zbollah
    -0.72
    Sov
    -0.68
    ãģķ
    -0.64
    Interstitial
    -0.59
    spread
    -0.59
    ãĤ·
    -0.58
    Compan
    -0.58
     conduc
    -0.57
    ãģĻ
    -0.57
     proxies
    -0.57
    POSITIVE LOGITS
     18
    3.02
     17
    2.24
     19
    2.15
     1840
    2.06
     16
    1.99
     1830
    1.97
     1850
    1.96
     1860
    1.96
     1886
    1.94
     1870
    1.93
    Act Density 0.039%

    No Known Activations