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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     faſt
    -0.95
     queſta
    -0.93
    ſelf
    -0.88
     houſe
    -0.81
    ſelves
    -0.81
     Houſe
    -0.77
     $_(
    -0.77
     ſch
    -0.77
     ſta
    -0.76
     ſche
    -0.75
    POSITIVE LOGITS
                
    1.41
    1.15
                                
    1.07
    0.98
                 
    0.90
                  
    0.88
                        
    0.87
                    
    0.81
               
    0.80
              
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.