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

    Neuronpedia

    INDEX
    Explanations

    technical instructions or advice related to programming or coding practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -1.00
    </i>
    -0.71
       
    -0.66
    </b>
    -0.65
    ’
    -0.60
     
    -0.50
    .\"
    -0.50
     
    -0.49
           
    -0.48
     \"
    -0.47
    POSITIVE LOGITS
    <code>
    1.88
    <em>
    1.20
    <sup>
    1.13
    <sub>
    0.88
    <s>
    0.84
    <strong>
    0.82
    AutoScaleMode
    0.71
     😄
    0.67
    <blockquote>
    0.63
    $^\
    0.63
    Act Density 1.977%

    No Known Activations