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

    Neuronpedia

    INDEX
    Explanations

    references to historical dating or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods and historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eye
    -0.81
    ucky
    -0.80
    overe
    -0.76
    ibrary
    -0.74
    atche
    -0.72
    osta
    -0.72
    oldemort
    -0.72
    ricular
    -0.72
    BLIC
    -0.70
    lain
    -0.70
    POSITIVE LOGITS
     Dating
    0.85
    dating
    0.67
    nis
    0.66
     antique
    0.65
    mers
    0.62
     dating
    0.62
     Sapphire
    0.61
    enance
    0.61
     antiquity
    0.60
     Apart
    0.59
    Act Density 0.025%

    No Known Activations