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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the pronoun "they."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.63
     Hins
    -0.62
     Thon
    -0.62
     fince
    -0.59
     purpoſe
    -0.59
     pomo
    -0.57
     Bue
    -0.56
     Nox
    -0.55
     šķ
    -0.55
     Monfieur
    -0.55
    POSITIVE LOGITS
     they
    2.91
    They
    2.49
     They
    2.47
    they
    2.34
     THEY
    2.24
    THEY
    2.21
     mereka
    1.70
     они
    1.63
     he
    1.63
    Mereka
    1.60
    Act Density 0.094%

    No Known Activations