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

    Neuronpedia

    INDEX
    Explanations

    references to policy and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebVitals
    -0.83
     FetchType
    -0.83
     CreateTagHelper
    -0.79
    IBarButtonItem
    -0.77
    żd
    -0.76
    uggets
    -0.76
    AndFlush
    -0.74
    ITHUB
    -0.74
    تقاوى
    -0.74
    czę
    -0.73
    POSITIVE LOGITS
     policies
    1.79
     policy
    1.75
     Policy
    1.62
     Policies
    1.57
    POLICY
    1.56
    Policy
    1.55
    policy
    1.51
     POLICY
    1.50
    Policies
    1.47
    policies
    1.32
    Act Density 0.031%

    No Known Activations