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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and court actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ă
    -0.84
    &#
    -0.83
    鈥
    -0.83
     
    -0.83
    窶
    -0.82
     &#
    -0.80
     $\$
    -0.76
     Ă
    -0.72
    -\\
    -0.71
     \$
    -0.69
    POSITIVE LOGITS
      
    4.00
       
    3.30
        
    2.56
         
    2.49
          
    2.43
           
    2.35
             
    2.16
               
    2.10
              
    2.09
            
    2.05
    Act Density 2.459%

    No Known Activations