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

    Neuronpedia

    INDEX
    Explanations

    statements related to questions or inquiries.

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

    questions and answers in a legal context.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    question-and-answer patterns in text, particularly in interview or interrogation transcripts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Follows a question

    np_acts-logits-general · gemini-2.0-flash

    gate electrode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.60
    ();
    -0.58
    .*;
    -0.56
    !")
    -0.56
    ！】
    -0.53
    :
    -0.53
    ();*/
    -0.51
    \\
    -0.50
    <bos>
    -0.50
     the
    -0.49
    POSITIVE LOGITS
     estekak
    1.06
     متعلقه
    1.00
    XmlAccessType
    0.96
    findpost
    0.90
    ValueStyle
    0.88
     بيها
    0.85
    DeleteBehavior
    0.84
    ISupport
    0.83
    >{@
    0.83
    ftagPool
    0.83
    Act Density 0.275%

    No Known Activations