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

    Neuronpedia

    INDEX
    Explanations

    mentions of nobility and titles in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.90
    NameInMap
    -0.87
     againſt
    -0.87
     Monfieur
    -0.86
     ſeveral
    -0.85
     himſelf
    -0.84
     kaynağından
    -0.84
     myſelf
    -0.83
     Majefty
    -0.83
     Theſe
    -0.82
    POSITIVE LOGITS
     medi
    0.47
    medi
    0.41
     specie
    0.41
     $
    0.40
     middle
    0.39
     mid
    0.38
    西装
    0.37
     Rosen
    0.37
     medio
    0.36
     [
    0.35
    Act Density 0.132%

    No Known Activations