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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated whitespace characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.64
    ↵↵
    -0.55
    Â
    -0.54
     and
    -0.52
    .
    -0.52
     —
    -0.52
    &#
    -0.51
    amp
    -0.50
    mu
    -0.47
    â
    -0.47
    POSITIVE LOGITS
                
    1.01
            
    1.00
             
    0.94
    ReusableCell
    0.94
                 
    0.92
               
    0.90
    fromnode
    0.89
              
    0.89
    SourceChecksum
    0.88
    InjectAttribute
    0.86
    Act Density 0.495%

    No Known Activations