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

    Neuronpedia

    INDEX
    Explanations

    years or date ranges

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and their associated events or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thumbs
    -0.68
     bets
    -0.67
     moder
    -0.67
     beads
    -0.66
    izon
    -0.66
     Dickinson
    -0.66
     antiv
    -0.65
     shade
    -0.64
     tolerance
    -0.64
    otine
    -0.63
    POSITIVE LOGITS
    mid
    0.95
    based
    0.94
    02
    0.94
    04
    0.94
    level
    0.92
    series
    0.92
    2020
    0.91
    09
    0.91
    12
    0.89
    08
    0.89
    Act Density 0.041%

    No Known Activations