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

    Neuronpedia

    INDEX
    Explanations

    references to political norms, rules, and conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cherchés
    -0.69
    endsection
    -0.58
     titulares
    -0.53
     المعيارى
    -0.52
    اصر
    -0.51
     inflater
    -0.51
     ReactDOM
    -0.51
     ventre
    -0.50
    崛起
    -0.50
     realizzazione
    -0.50
    POSITIVE LOGITS
     rules
    1.49
    rules
    1.28
     Rules
    1.26
    RULES
    1.18
     RULES
    1.15
    Rules
    1.15
     rule
    1.09
     guidelines
    1.07
     Regeln
    1.06
     standards
    1.01
    Act Density 0.488%

    No Known Activations