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

    Neuronpedia

    INDEX
    Explanations

    long sequences of whitespace or specific formatting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.79
     RemoteException
    -0.78
    endmodule
    -0.76
     continúas
    -0.74
    imarães
    -0.73
    DOCTYPE
    -0.73
     Yoo
    -0.73
    formKey
    -0.73
    mappedBy
    -0.72
    édia
    -0.71
    POSITIVE LOGITS
         
    1.55
             
    1.20
          
    1.17
        
    1.15
           
    1.15
                 
    1.10
            
    1.04
    1.04
       
    1.03
    1.01
    Act Density 0.094%

    No Known Activations