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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas and parentheses

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

    closing quotes and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chriftian
    -0.69
     Jefus
    -0.56
     ſur
    -0.53
     culte
    -0.53
    تقاوى
    -0.52
     Houſe
    -0.52
     Inſ
    -0.52
     purpoſe
    -0.51
    <bos>
    -0.51
     мәкал
    -0.51
    POSITIVE LOGITS
    `,
    1.35
    `)
    1.05
    `.
    1.00
    >`;
    0.97
    }`,
    0.95
     `,
    0.94
    `;
    0.93
    `);
    0.92
    `),
    0.90
    `).
    0.89
    Act Density 0.017%

    No Known Activations