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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters or tokens in a structured format, such as code or markup syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -1.23
     تضيفلها
    -1.18
     AssemblyVersion
    -1.02
    ſelves
    -1.00
     myſelf
    -0.99
    UserScript
    -0.99
     ་་
    -0.97
     ―――――
    -0.96
     itſelf
    -0.96
     Majefty
    -0.96
    POSITIVE LOGITS
      
    0.80
     ces
    0.72
               
    0.71
              
    0.71
                          
    0.67
           
    0.65
                  
    0.65
                      
    0.63
     
    0.61
                   
    0.60
    Act Density 0.426%

    No Known Activations