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

    Neuronpedia

    INDEX
    Explanations

    references to events that occurred a specific number of years in the past

    oai_token-act-pair · gpt-3.5-turbo

    reference to time periods in the past, specifically events that occurred 'years ago' or 'months ago'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aspx
    -0.78
    lua
    -0.77
    izoph
    -0.66
    nce
    -0.65
     Sync
    -0.65
    amins
    -0.63
    irc
    -0.63
    eers
    -0.62
    iframe
    -0.62
    ym
    -0.62
    POSITIVE LOGITS
    opausal
    0.90
     mornings
    0.76
     when
    0.70
    rolet
    0.69
     ago
    0.65
    orescence
    0.65
    agher
    0.64
     afternoon
    0.63
    abi
    0.63
     testify
    0.61
    Act Density 0.027%

    No Known Activations