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

    Neuronpedia

    INDEX
    Explanations

    dates in the 1920s, 1930s, and 1940s

    oai_token-act-pair · gpt-3.5-turbo

    specific historical years or dates relevant to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    por
    -0.69
    ror
    -0.64
    ioned
    -0.64
    opher
    -0.62
    lez
    -0.62
    task
    -0.60
    erate
    -0.60
     twe
    -0.58
    spin
    -0.58
     webcam
    -0.58
    POSITIVE LOGITS
     1936
    0.85
     1935
    0.85
     1939
    0.85
     1938
    0.84
     1934
    0.82
     1933
    0.81
     Churchill
    0.80
    -'
    0.79
     1937
    0.78
     1914
    0.77
    Act Density 0.051%

    No Known Activations