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

    Neuronpedia

    INDEX
    Explanations

    references to time periods in history

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods and ages in years or millions of years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.74
     Sack
    -0.74
    WN
    -0.66
     Franch
    -0.64
    ilyn
    -0.64
    Sing
    -0.64
    Focus
    -0.63
     Greenberg
    -0.63
    essa
    -0.62
    Priv
    -0.61
    POSITIVE LOGITS
     ago
    1.59
     Ago
    1.14
     old
    1.13
     olds
    1.07
     BCE
    0.97
    Old
    0.91
     extinct
    0.90
     distant
    0.88
     BP
    0.85
     BC
    0.85
    Act Density 0.052%

    No Known Activations