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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases such as time durations and specific points in time

    oai_token-act-pair · gpt-3.5-turbo

    references to time duration and elapsed periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.80
    emale
    -0.72
    anooga
    -0.70
    MODE
    -0.70
    nels
    -0.67
    plex
    -0.67
    minecraft
    -0.66
    duction
    -0.66
     subsistence
    -0.65
    liction
    -0.65
    POSITIVE LOGITS
     Ago
    1.28
     ago
    1.25
     elapsed
    0.85
     shy
    0.81
     apiece
    0.76
    ccording
    0.73
     hindsight
    0.72
     Months
    0.71
     passed
    0.70
    long
    0.69
    Act Density 0.106%

    No Known Activations