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

    Neuronpedia

    INDEX
    Explanations

    dialogue phrases indicating acknowledgment or questioning

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

    Follows a question mark or colon

    np_acts-logits-general · gemini-2.0-flash

    question-and-answer dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.12
    RenderAtEndOf
    -1.06
    "):
    -0.99
     myſelf
    -0.96
    ".
    -0.92
    gameserver
    -0.90
    $.
    -0.90
     ſind
    -0.89
    `,
    -0.89
    "])
    -0.88
    POSITIVE LOGITS
    Yeah
    0.78
    And
    0.76
     Yeah
    0.70
    So
    0.70
     And
    0.66
    .
    0.65
    Oh
    0.63
     [
    0.62
     (
    0.62
     .
    0.62
    Act Density 0.127%

    No Known Activations