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

    Neuronpedia

    INDEX
    Explanations

    complex numeric structures or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bote
    -0.97
    ly
    -0.94
     ―――――
    -0.92
     Efq
    -0.92
    aarrggbb
    -0.90
     auffi
    -0.88
     Hanne
    -0.87
     neceffary
    -0.87
    ContextHolder
    -0.85
     $_"
    -0.84
    POSITIVE LOGITS
       
    1.55
      
    0.98
    קישורים
    0.84
      
    0.77
                               
    0.75
                       
    0.73
                      
    0.71
    0.70
                   
    0.67
               
    0.67
    Act Density 0.143%

    No Known Activations