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

    Neuronpedia

    INDEX
    Explanations

    formatted text elements and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.67
    ↵↵
    -0.62
    ↵
    -0.61
    <eos>
    -0.57
     occidentale
    -0.55
      
    -0.54
    ↵↵↵↵↵
    -0.50
       
    -0.49
     confiable
    -0.48
    ↵↵↵↵
    -0.47
    POSITIVE LOGITS
    Portale
    1.02
    rungsseite
    0.98
    tagHelperRunner
    0.95
     pinulongan
    0.93
     nahilalakip
    0.92
    principalTable
    0.91
     للاسماء
    0.86
    AsUp
    0.81
    تقاوى
    0.81
     تضيفلها
    0.79
    Act Density 0.057%

    No Known Activations