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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related words

    oai_token-act-pair · gpt-3.5-turbo

    temporal references to events and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icates
    -0.67
    ggles
    -0.66
    tains
    -0.64
    icators
    -0.60
    ication
    -0.60
     Transactions
    -0.57
    rouse
    -0.57
     maximal
    -0.57
     fixation
    -0.57
     Ratings
    -0.57
    POSITIVE LOGITS
    rolet
    0.76
     owing
    0.70
    ullah
    0.69
    izu
    0.68
     mornings
    0.67
     aged
    0.66
     semester
    0.66
     afternoon
    0.66
     endorsing
    0.65
    vernight
    0.64
    Act Density 0.228%

    No Known Activations