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

    Neuronpedia

    INDEX
    Explanations

    timeframes mentioned in years

    oai_token-act-pair · gpt-3.5-turbo

    references to timeframes or projections related to future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.82
    @#&
    -0.81
    76561
    -0.64
     seiz
    -0.64
    wered
    -0.62
    ighed
    -0.61
     grate
    -0.60
     Doct
    -0.59
     valiant
    -0.58
    vu
    -0.58
    POSITIVE LOGITS
     months
    1.10
     years
    1.07
     weeks
    1.01
     2020
    1.01
     2019
    0.99
    2019
    0.98
    months
    0.95
    years
    0.94
    2020
    0.94
    morrow
    0.91
    Act Density 0.142%

    No Known Activations