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

    Neuronpedia

    INDEX
    Explanations

    references to formal structures or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tigungs
    -0.62
    tigung
    -0.61
     McCann
    -0.60
     Lieferung
    -0.60
     McDonough
    -0.59
     Trigonometry
    -0.59
     Navig
    -0.58
     polymorphism
    -0.57
     prophecy
    -0.57
     Erhöhung
    -0.57
    POSITIVE LOGITS
    Formal
    2.96
     Formal
    2.95
     formal
    2.93
    formal
    2.71
     formally
    2.38
     formales
    2.18
     formalized
    2.00
     informal
    1.91
     Informal
    1.87
    Informal
    1.74
    Act Density 0.142%

    No Known Activations