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

    Neuronpedia

    INDEX
    Explanations

    references to legal rules and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.89
    Personensuche
    -0.87
    ︎
    -0.85
     Humphreys
    -0.84
    enuine
    -0.84
    +</
    -0.83
    Cordialement
    -0.80
    endsection
    -0.79
     Hartmann
    -0.79
     @}
    -0.78
    POSITIVE LOGITS
     rules
    1.81
     rule
    1.71
     Rules
    1.67
     Rule
    1.64
     RULE
    1.61
    Rules
    1.53
     RULES
    1.51
    rules
    1.50
    Rule
    1.42
    RULE
    1.36
    Act Density 0.069%

    No Known Activations