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

    Neuronpedia

    INDEX
    Explanations

    dates related to specific historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, particularly during World War II

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atives
    -0.78
    ative
    -0.77
    hed
    -0.73
    ator
    -0.72
    ional
    -0.71
    att
    -0.70
    essee
    -0.70
    keys
    -0.70
    amin
    -0.70
    inqu
    -0.70
    POSITIVE LOGITS
     1942
    1.16
     1943
    1.13
     1944
    1.10
     1941
    1.05
     1939
    0.99
     1938
    0.95
     1937
    0.94
     1914
    0.90
     1945
    0.90
     1936
    0.90
    Act Density 0.016%

    No Known Activations