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

    Neuronpedia

    INDEX
    Explanations

    references to time duration, specifically in years or decades

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time, specifically the expression of years and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dice
    -0.61
    jac
    -0.57
    ukes
    -0.56
    inite
    -0.55
    Fit
    -0.54
    eret
    -0.53
     Gran
    -0.52
    ensen
    -0.51
    Ni
    -0.51
     Load
    -0.50
    POSITIVE LOGITS
     ago
    2.00
     Ago
    1.44
     earlier
    1.27
     later
    1.07
     prior
    1.04
     previously
    1.01
     beforehand
    0.98
     before
    0.91
    later
    0.86
     previous
    0.84
    Act Density 0.054%

    No Known Activations