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

    Neuronpedia

    INDEX
    Explanations

    terms related to traditional or old-fashioned concepts or items

    oai_token-act-pair · gpt-3.5-turbo

    references to traditional and nostalgic elements in culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essional
    -0.91
    ealous
    -0.88
    edi
    -0.82
    overe
    -0.79
    pport
    -0.77
    atoon
    -0.77
    uliffe
    -0.76
    uclear
    -0.76
    iversal
    -0.75
    iev
    -0.73
    POSITIVE LOGITS
     fashioned
    0.85
    fashioned
    0.75
     obsolete
    0.73
     relics
    0.72
     carc
    0.67
     Carth
    0.65
     Julius
    0.64
     Till
    0.64
     outdated
    0.64
     Cemetery
    0.64
    Act Density 0.243%

    No Known Activations