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

    Neuronpedia

    INDEX
    Explanations

    codes or references related to age or time

    oai_token-act-pair · gpt-3.5-turbo

    references to age-related topics or age itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     steadfast
    -0.68
     loyal
    -0.67
     tri
    -0.61
    ãĥĪ
    -0.60
     vain
    -0.59
     united
    -0.59
     cz
    -0.59
     stressed
    -0.57
     unified
    -0.57
     Tri
    -0.57
    POSITIVE LOGITS
    AGE
    4.66
    AGES
    3.52
    ages
    2.66
    age
    2.53
    aging
    2.14
    aged
    2.06
    agement
    1.58
    agers
    1.57
    AG
    1.52
    ager
    1.42
    Act Density 0.008%

    No Known Activations