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

    Neuronpedia

    INDEX
    Explanations

    sections of the text with numerical data or significant figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </h6>
    -0.81
    -​
    -0.74
     ​
    -0.73
    </h4>
    -0.73
    ​
    -0.69
     
    -0.69
    <strong>
    -0.69
    <h4>
    -0.69
    </strong>
    -0.67
    <em>
    -0.67
    POSITIVE LOGITS
    훙
    0.68
    \
    0.63
    ㄸ
    0.61
    눙
    0.60
    푼
    0.60
    ๔
    0.58
    ״
    0.58
    ङ
    0.57
    ㄷ
    0.56
    ๑
    0.55
    Act Density 0.198%

    No Known Activations