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

    Neuronpedia

    INDEX
    Explanations

    sequences of identical characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.83
    complexContent
    -0.82
    NYSE
    -0.79
    EDEFAULT
    -0.76
    Ecotoxicity
    -0.73
    떻
    -0.72
    featureID
    -0.72
     Heid
    -0.72
    endmodule
    -0.71
     sine
    -0.71
    POSITIVE LOGITS
                    
    1.72
                     
    1.44
                   
    1.43
                      
    1.37
    1.33
                  
    1.30
                       
    1.24
    1.22
                 
    1.18
                        
    1.12
    Act Density 0.523%

    No Known Activations