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

    Neuronpedia

    INDEX
    Explanations

    dates referred to as "late"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "late" associated with dates or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apego
    -0.88
    inguished
    -0.83
    ourge
    -0.76
     Preferred
    -0.68
    IUM
    -0.66
    quished
    -0.65
    hyde
    -0.63
    abilia
    -0.63
    utenberg
    -0.62
    ylum
    -0.62
    POSITIVE LOGITS
     infancy
    0.89
     increments
    0.89
     gestation
    0.83
     afternoon
    0.82
    imester
    0.80
     mornings
    0.80
     adolescence
    0.78
    jection
    0.77
    flight
    0.77
     chronological
    0.76
    Act Density 0.040%

    No Known Activations