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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to time, particularly the term "year" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proverbial
    -0.65
    venge
    -0.59
     chore
    -0.57
    existent
    -0.56
     plumbing
    -0.56
     choke
    -0.56
     kindred
    -0.55
     favour
    -0.55
     metaph
    -0.55
     Himself
    -0.54
    POSITIVE LOGITS
     meanwhile
    0.78
     however
    0.72
    quickShipAvailable
    0.69
    nces
    0.61
    !--
    0.59
     Files
    0.58
    onnaissance
    0.57
    hawks
    0.57
    ombie
    0.56
    aucus
    0.56
    Act Density 0.471%

    No Known Activations