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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns related to identity and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.91
     ſever
    -0.88
     auffi
    -0.81
     yourselves
    -0.81
     purpoſe
    -0.79
    ergies
    -0.79
     faſt
    -0.79
     raiſ
    -0.77
     itſelf
    -0.77
     perſon
    -0.76
    POSITIVE LOGITS
     his
    1.59
     His
    1.35
     HIS
    1.27
    His
    1.26
    his
    1.18
     her
    1.16
    HIS
    1.15
     hers
    0.94
     Her
    0.88
    他的
    0.88
    Act Density 0.251%

    No Known Activations