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

    Neuronpedia

    INDEX
    Explanations

    references to authority and authoritative figures or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     архивлан
    -0.71
     nahilalakip
    -0.70
    /*---
    -0.62
     >=",
    -0.59
    AccessorTable
    -0.57
    PyExc
    -0.56
    estacks
    -0.55
     ***!
    -0.55
     Timp
    -0.54
    serves
    -0.54
    POSITIVE LOGITS
     authority
    1.47
    Authority
    1.35
    authority
    1.33
     AUTHORITY
    1.25
     Authority
    1.20
     auth
    0.95
     authorities
    0.93
    authorities
    0.91
     AUTHORITIES
    0.86
     autoridad
    0.85
    Act Density 0.090%

    No Known Activations