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

    Neuronpedia

    INDEX
    Explanations

    structured data formatting elements in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reſ
    -1.03
     autorytatywna
    -0.95
     Majefty
    -0.94
     Houſe
    -0.94
     Anſ
    -0.93
     itſelf
    -0.93
     iſt
    -0.92
     Eſ
    -0.92
     Theſe
    -0.92
     Conſ
    -0.86
    POSITIVE LOGITS
     "
    0.76
    .
    0.63
    </h2>
    0.63
     C
    0.63
     “
    0.59
      
    0.58
     K
    0.56
     (
    0.56
    ↵
    0.55
    ↵↵
    0.54
    Act Density 0.141%

    No Known Activations