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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated characters or whitespace in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.99
    aarrggbb
    -0.90
     $_"
    -0.86
    atimes
    -0.86
    WebServlet
    -0.85
    featureID
    -0.84
     חיצוניים
    -0.84
    formKey
    -0.83
     Overture
    -0.80
     Bote
    -0.80
    POSITIVE LOGITS
       
    1.60
         
    1.07
           
    1.04
        
    1.02
             
    1.01
      
    0.99
    0.98
    קישורים
    0.98
               
    0.97
                   
    0.94
    Act Density 0.170%

    No Known Activations