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

    Neuronpedia

    INDEX
    Explanations

    control flow statements and programming structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -1.57
     iſt
    -1.47
     ſind
    -1.46
     itſelf
    -1.45
     myſelf
    -1.42
     ་་
    -1.40
     Efq
    -1.36
     XNUMX
    -1.34
     ―――――
    -1.34
     $_"
    -1.34
    POSITIVE LOGITS
      
    1.27
    ↵
    1.23
    <eos>
    1.14
       
    1.03
     
    1.01
     ,
    0.98
        
    0.95
    ↵↵↵
    0.93
    ↵↵
    0.92
         
    0.81
    Act Density 0.206%

    No Known Activations