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

    Neuronpedia

    INDEX
    Explanations

    elements related to formal documentation and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -1.12
    ↵↵↵
    -0.77
    ↵↵↵↵
    -0.76
      
    -0.74
    ↵↵↵↵↵
    -0.71
    ↵
    -0.70
    ↵↵↵↵↵↵↵
    -0.66
     …
    -0.66
    ↵↵↵↵↵↵↵↵
    -0.65
    </blockquote>
    -0.64
    POSITIVE LOGITS
    uxxxx
    1.06
    GEBURTSDATUM
    1.00
     Мексичка
    1.00
     Италијани
    0.99
     ویکی‌پدی
    0.95
     autorytatywna
    0.92
    InjectAttribute
    0.91
    RTEE
    0.90
     дописавши
    0.88
     الحره
    0.85
    Act Density 0.809%

    No Known Activations