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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns, particularly "his"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Оно
    -0.76
     Agamemnon
    -0.65
    נטרנט
    -0.62
     Plutarch
    -0.61
     Parthen
    -0.60
     ää
    -0.59
     Sopho
    -0.58
     Monfieur
    -0.58
     Platon
    -0.56
     Egl
    -0.56
    POSITIVE LOGITS
     his
    2.93
    his
    2.29
     HIS
    2.14
     His
    2.04
    His
    2.02
    HIS
    1.93
    他的
    1.67
     그의
    1.63
    彼の
    1.61
     seiner
    1.60
    Act Density 0.101%

    No Known Activations