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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    "How
    -0.07
    、『
    -0.07
    なんて
    -0.07
     spinning
    -0.07
     //"
    -0.07
    -cal
    -0.06
    }],↵
    -0.06
    afx
    -0.06
    *c
    -0.06
     pán
    -0.06
    POSITIVE LOGITS
    0.08
      
    0.08
        
    0.08
            
    0.07
      
    0.07
     　　
    0.07
          
    0.07
     premium
    0.07
    -tool
    0.06
     sito
    0.06
    Act Density 0.011%

    No Known Activations