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

    Neuronpedia

    INDEX
    Explanations

    narratives about historical artifacts and women's roles in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     statue
    -0.15
     monument
    -0.15
     monuments
    -0.14
     gravel
    -0.14
    icle
    -0.14
     critically
    -0.14
    etr
    -0.14
    opoulos
    -0.14
     mole
    -0.14
    aurus
    -0.14
    POSITIVE LOGITS
     rare
    0.32
     Rare
    0.28
    Rare
    0.26
     rarity
    0.24
     scarce
    0.23
     ephem
    0.21
     early
    0.20
     earliest
    0.19
     ÑĢед
    0.19
     collect
    0.18
    Act Density 0.112%

    No Known Activations