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

    Neuronpedia

    INDEX
    Explanations

    references to royal or noble seats of authority

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    __':
    -0.68
    -0.58
    PageModule
    -0.57
    astéroïdes
    -0.57
    astify
    -0.55
    fjspx
    -0.52
     mAdapter
    -0.50
    __":
    -0.50
    gebouw
    -0.49
     flatten
    -0.49
    POSITIVE LOGITS
     throne
    3.89
     Throne
    2.80
     trono
    2.27
     thrones
    1.89
     trône
    1.83
     Thron
    1.50
     crown
    0.79
    ftagPool
    0.79
     Thrones
    0.75
     sceptre
    0.74
    Act Density 0.001%

    No Known Activations