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

    Neuronpedia

    INDEX
    Explanations

    years or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to historical periods and significant movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.89
    tackle
    -0.78
     violates
    -0.74
    ationally
    -0.72
    pez
    -0.70
    cheat
    -0.69
    AMI
    -0.69
    wayne
    -0.67
    bnb
    -0.67
    ivo
    -0.66
    POSITIVE LOGITS
     1930
    1.69
     1960
    1.60
     1920
    1.59
     1890
    1.57
     1950
    1.56
     1970
    1.54
     1880
    1.54
     1870
    1.53
     1940
    1.52
     1840
    1.52
    Act Density 0.205%

    No Known Activations