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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, specifically focusing on spans of years

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.85
    anooga
    -0.71
    eus
    -0.70
    ibrary
    -0.69
     subp
    -0.62
    liction
    -0.61
    acly
    -0.61
    esc
    -0.60
    enburg
    -0.60
    abeth
    -0.59
    POSITIVE LOGITS
     ago
    1.62
     Ago
    1.32
     olds
    1.19
     old
    0.96
     elapsed
    0.85
     overdue
    0.82
     apiece
    0.80
     hindsight
    0.76
    ago
    0.75
    old
    0.73
    Act Density 0.433%

    No Known Activations