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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    исленность
    -0.56
     Huerta
    -0.55
     oprot
    -0.53
    port
    -0.52
     Dill
    -0.52
     ports
    -0.52
     Keaton
    -0.52
    ENR
    -0.51
    ports
    -0.51
    derby
    -0.51
    POSITIVE LOGITS
                    
    1.18
                   
    0.73
     fifth
    0.71
     Fifth
    0.67
                     
    0.67
                  
    0.65
    五
    0.63
     five
    0.61
    fifth
    0.59
    Fifth
    0.58
    Act Density 0.169%

    No Known Activations