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

    Neuronpedia

    INDEX
    Explanations

    the presence of characters and their actions or relationships in a narrative context

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

    your, yours, yourself

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of third-person personal pronouns (especially singular forms like "he"/"she"/"he's") referring to people.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.64
     שוליים
    -0.61
    providedIn
    -0.61
    principalColumn
    -0.54
    CloseOperation
    -0.51
    WebServlet
    -0.49
     الحره
    -0.49
     esternos
    -0.45
    exitRule
    -0.43
    makeText
    -0.42
    POSITIVE LOGITS
     your
    0.74
     yourself
    0.68
    your
    0.65
     yours
    0.59
     yourselves
    0.56
    Your
    0.56
    Yourself
    0.50
     ваших
    0.50
     YOURSELF
    0.48
     вашим
    0.47
    Act Density 0.905%

    No Known Activations