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

    Neuronpedia

    INDEX
    Explanations

    references to specific historical time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to the early days of various decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.82
    avorite
    -0.79
    oppable
    -0.72
    osate
    -0.69
    quished
    -0.69
     chained
    -0.68
    IDA
    -0.68
    iscopal
    -0.68
    cham
    -0.66
    dain
    -0.66
    POSITIVE LOGITS
     twenties
    1.14
     1980
    1.07
     1990
    1.07
    ixties
    1.06
     stages
    1.05
     1970
    1.01
     1960
    1.01
     2000
    0.98
     phases
    0.96
     days
    0.95
    Act Density 0.049%

    No Known Activations