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

    Neuronpedia

    INDEX
    Explanations

    patterns or structured delimiters in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -1.12
     ―――――
    -1.03
     Vedi
    -0.96
    cerely
    -0.95
    ChildScrollView
    -0.92
    >`;
    -0.91
     Dami
    -0.91
     repatri
    -0.90
     Anſ
    -0.89
     Simeon
    -0.85
    POSITIVE LOGITS
         
    1.82
        
    1.13
       
    1.04
    0.90
    0.84
                 
    0.82
                        
    0.79
           
    0.78
     Wight
    0.74
    _{
    0.73
    Act Density 0.117%

    No Known Activations