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

    Neuronpedia

    INDEX
    Explanations

    repeated sequences or patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.96
    %";
    -0.85
     AssemblyVersion
    -0.83
    <%=
    -0.82
    er
    -0.81
    %");
    -0.75
    %;
    -0.75
     فريبيس
    -0.74
     drag
    -0.72
     <",
    -0.72
    POSITIVE LOGITS
        
    2.08
         
    1.57
            
    1.52
          
    1.51
                
    1.50
    1.46
       
    1.44
                        
    1.43
           
    1.35
      
    1.30
    Act Density 0.230%

    No Known Activations