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

    Neuronpedia

    INDEX
    Explanations

    years or dates from the early 1900s

    oai_token-act-pair · gpt-3.5-turbo

    specific years, particularly in the early 1900s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iant
    -0.78
    egal
    -0.77
    ende
    -0.76
    kell
    -0.69
    affer
    -0.69
    las
    -0.67
    amination
    -0.67
    sequence
    -0.66
    inqu
    -0.66
    hedral
    -0.65
    POSITIVE LOGITS
     1909
    1.01
     1903
    0.95
     1905
    0.95
     1906
    0.94
    ĸļ
    0.92
     1908
    0.87
     1934
    0.84
     1912
    0.83
     1910
    0.83
     1904
    0.83
    Act Density 0.011%

    No Known Activations