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

    Neuronpedia

    INDEX
    Explanations

    numeric expressions referring to quantities of time

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly ages and quantities, related to individuals and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rium
    -0.76
     tomorrow
    -0.63
     backdrop
    -0.62
     Huck
    -0.62
    abus
    -0.61
     tension
    -0.61
    aeus
    -0.61
    atum
    -0.60
     crest
    -0.60
     subset
    -0.60
    POSITIVE LOGITS
     years
    1.30
    years
    1.21
     consecutive
    1.16
     stint
    1.08
     seasons
    1.07
     months
    1.07
     winters
    1.05
     summers
    1.04
    months
    1.01
     Years
    1.00
    Act Density 0.187%

    No Known Activations