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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "I"

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

    pronoun I at the start of text

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

    Detecting first-person self-reference — when the speaker refers to themselves (the pronoun "I").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.75
     Numerade
    -0.71
    aarrggbb
    -0.68
    ACHUSET
    -0.67
    Personensuche
    -0.60
    delwed
    -0.59
    setVerticalGroup
    -0.59
    -------
    -0.58
    titleMargin
    -0.57
    forChild
    -0.57
    POSITIVE LOGITS
     I
    0.73
    I
    0.65
     Im
    0.49
    Im
    0.48
    Is
    0.40
     my
    0.39
    Var
    0.38
     questions
    0.38
    In
    0.38
    My
    0.38
    Act Density 0.076%

    No Known Activations