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

    Neuronpedia

    INDEX
    Explanations

    references to official documents and treaties related to governance and independence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     markets
    -0.79
    bably
    -0.72
     worsh
    -0.71
    iannopoulos
    -0.71
    anced
    -0.71
    itably
    -0.70
    ictions
    -0.69
    ibly
    -0.67
     restrooms
    -0.67
     perjury
    -0.66
    POSITIVE LOGITS
     Agreement
    1.06
     Collection
    1.01
     Declaration
    0.95
     Address
    0.95
     Implementation
    0.94
     Generator
    0.94
     Letters
    0.92
     Package
    0.92
     Memor
    0.91
     Programme
    0.91
    Act Density 0.060%

    No Known Activations