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

    Neuronpedia

    INDEX
    Explanations

    structured legal terms and references relevant to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faſt
    -0.88
     raiſ
    -0.85
    ſelves
    -0.82
     houſe
    -0.82
     Houſe
    -0.81
     ſche
    -0.77
    ſelf
    -0.77
     pleaſure
    -0.77
     tranſ
    -0.75
     ſta
    -0.75
    POSITIVE LOGITS
          
    1.31
           
    0.93
                  
    0.93
                          
    0.91
                        
    0.81
         
    0.78
                         
    0.77
    0.77
              
    0.76
                      
    0.75
    Act Density 0.209%

    No Known Activations