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

    Neuronpedia

    INDEX
    Explanations

    references to the second person, specifically the use of "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.58
    :✨
    -0.50
    ppincott
    -0.49
    gypte
    -0.49
     }}}
    -0.48
     }}$}
    -0.47
    aarrggbb
    -0.47
     Италијани
    -0.47
    aternion
    -0.47
    ksanakan
    -0.47
    POSITIVE LOGITS
     You
    0.90
    You
    0.81
    There
    0.49
    It
    0.48
    Your
    0.48
     It
    0.47
     If
    0.47
    YOU
    0.47
     There
    0.46
    If
    0.46
    Act Density 0.022%

    No Known Activations