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

    Neuronpedia

    INDEX
    Explanations

    concepts related to philosophy and policy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.71
    AntiForgeryToken
    -0.70
     domestiques
    -0.66
     réparation
    -0.65
     étan
    -0.65
     médicaux
    -0.65
     auroit
    -0.65
     feroit
    -0.64
     romantique
    -0.64
     rhestr
    -0.64
    POSITIVE LOGITS
     approach
    1.22
     attitude
    1.21
    approach
    0.98
     philosophy
    0.96
    attitude
    0.95
     strategy
    0.95
     policy
    0.94
     attitudes
    0.92
     policies
    0.91
     Approach
    0.91
    Act Density 0.415%

    No Known Activations