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

    Neuronpedia

    INDEX
    Explanations

    mentions of past events or time-related actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of the "past."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shapeshifter
    -0.75
    wagon
    -0.73
    starting
    -0.70
    NEY
    -0.67
     Skydragon
    -0.60
    strap
    -0.58
     GENERAL
    -0.56
    lee
    -0.55
     thereafter
    -0.55
    alert
    -0.54
    POSITIVE LOGITS
    ebin
    1.73
    ures
    1.29
    imes
    1.29
    ime
    1.28
    iche
    1.27
    orate
    1.18
    oral
    1.15
     tense
    1.12
    ries
    1.10
    ured
    0.95
    Act Density 0.027%

    No Known Activations