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

    Neuronpedia

    INDEX
    Explanations

    dates represented in four-digit format

    oai_token-act-pair · gpt-3.5-turbo

    specific years, predominantly in the early 20th century

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ularity
    -0.75
    egal
    -0.70
    iant
    -0.68
    anamo
    -0.67
    las
    -0.67
    ular
    -0.67
    RAM
    -0.66
    Resource
    -0.66
    ende
    -0.65
     blockers
    -0.63
    POSITIVE LOGITS
     1909
    0.87
     1906
    0.84
     1905
    0.82
     1903
    0.80
     1908
    0.78
    £ı
    0.78
     1907
    0.77
     1912
    0.77
     1910
    0.75
     1934
    0.73
    Act Density 0.011%

    No Known Activations