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

    Neuronpedia

    INDEX
    Explanations

    structured programming elements and HTML tags in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused43>
    -1.18
    <unused42>
    -1.18
    <unused23>
    -1.18
    <unused41>
    -1.18
    <unused3>
    -1.18
    <pad>
    -1.18
    <unused8>
    -1.18
    <unused16>
    -1.18
    <unused68>
    -1.18
    <unused74>
    -1.18
    POSITIVE LOGITS
    ↵↵
    0.95
    ↵
    0.87
     //
    0.80
    ↵↵↵
    0.78
    ↵↵↵↵
    0.75
    //
    0.73
       
    0.73
      
    0.71
           
    0.65
         
    0.64
    Act Density 0.599%

    No Known Activations