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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with code or data processing functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ."</
    -1.09
    %</
    -1.03
    Rhestr
    -1.00
    PerformLayout
    -0.99
    +</
    -0.97
     continúas
    -0.94
    EndContext
    -0.93
     OkHttpClient
    -0.91
    ,</
    -0.91
     DialogInterface
    -0.88
    POSITIVE LOGITS
    <eos>
    0.91
    0.84
        
    0.84
    ↵↵
    0.83
                                
    0.82
    0.80
    0.80
                            
    0.79
                    
    0.78
    0.77
    Act Density 0.061%

    No Known Activations