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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to the self, particularly the word "I"

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

    I/je followed by personal statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.70
     cherchés
    -0.68
    UserScript
    -0.67
    +#+#
    -0.65
     Мексичка
    -0.65
     }}"></
    -0.65
     FetchType
    -0.64
     estekak
    -0.64
     ProtoMessage
    -0.64
     الرياضيه
    -0.64
    POSITIVE LOGITS
     kiin
    0.37
     bahía
    0.36
     patas
    0.34
     pulseira
    0.34
     academic
    0.34
     aprendiz
    0.33
     noy
    0.33
     acadé
    0.32
     marins
    0.32
     keskus
    0.31
    Act Density 0.015%

    No Known Activations