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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and identity in terms of pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agn
    -0.14
    azon
    -0.14
     Authorities
    -0.13
    endra
    -0.13
    arks
    -0.13
    ouse
    -0.13
    庫
    -0.13
    едж
    -0.13
    ade
    -0.13
     Zus
    -0.13
    POSITIVE LOGITS
    iaux
    0.16
    utex
    0.16
    iyet
    0.15
    ãĥ¼ãĥĹ
    0.14
    626
    0.14
    /wp
    0.14
    acha
    0.13
    _WP
    0.13
     Rao
    0.13
    tracts
    0.13
    Act Density 0.033%

    No Known Activations