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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    the word "Your" in various contexts, indicating a focus on addressing the reader directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     counterparts
    -0.63
     overt
    -0.62
     pan
    -0.61
     mixed
    -0.60
     counterpart
    -0.60
     record
    -0.60
     equivalents
    -0.60
     across
    -0.60
     efforts
    -0.58
     pot
    -0.57
    POSITIVE LOGITS
    Your
    3.37
    your
    2.56
     Your
    2.08
     YOUR
    1.80
    You
    1.71
    YOU
    1.50
    Congratulations
    1.44
    Our
    1.43
     your
    1.42
     Yourself
    1.39
    Act Density 0.015%

    No Known Activations