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

    Neuronpedia

    INDEX
    Explanations

    long sequences or placeholders in text formats, likely indicating structured data or markup elements

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

    UI components, buttons, forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.68
    <unused68>
    -1.48
    <unused8>
    -1.48
    <unused41>
    -1.48
    <unused16>
    -1.47
    <unused3>
    -1.47
    <unused28>
    -1.47
    <unused43>
    -1.47
    <pad>
    -1.47
    [@BOS@]
    -1.47
    POSITIVE LOGITS
     
    0.58
    2
    0.58
        
    0.57
      
    0.55
    1
    0.51
    0
    0.50
            
    0.49
    0.49
    4
    0.48
    3
    0.48
    Act Density 0.033%

    No Known Activations