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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated characters or patterns

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

    XML tags and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.44
    iſchen
    -1.13
     betweenstory
    -1.13
    нгред
    -1.11
    niſſe
    -1.11
    ſſung
    -1.10
     vooz
    -1.10
    ロウィン
    -1.09
     témoig
    -1.09
    parsedMessage
    -1.09
    POSITIVE LOGITS
        
    1.34
    0.96
         
    0.92
                        
    0.91
                
    0.90
       
    0.83
            
    0.83
          
    0.79
      
    0.70
                    
    0.70
    Act Density 0.231%

    No Known Activations