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

    Neuronpedia

    INDEX
    Explanations

    words related to the passage of time, specifically focusing on recent or ongoing events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the occurrence of events over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usable
    -0.70
     dispute
    -0.68
     opposes
    -0.63
    abuse
    -0.63
     basal
    -0.63
    reply
    -0.62
    USE
    -0.62
    counter
    -0.61
    inance
    -0.59
    uations
    -0.59
    POSITIVE LOGITS
     been
    1.16
     begun
    1.01
     gone
    0.98
     seen
    0.97
     flown
    0.96
     gotten
    0.94
     undergone
    0.92
     proven
    0.92
     yielded
    0.91
     taught
    0.89
    Act Density 0.120%

    No Known Activations