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

    Neuronpedia

    INDEX
    Explanations

    references to federal legal standards or rulings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.68
     getIs
    -0.66
    hassee
    -0.58
     Arora
    -0.57
    UCL
    -0.55
     Stanton
    -0.54
     ent
    -0.53
    cluse
    -0.52
    allax
    -0.52
    entityManager
    -0.51
    POSITIVE LOGITS
    Fed
    1.19
     Fed
    1.05
     uſed
    1.04
     fevere
    1.00
     Majefty
    1.00
     ſever
    0.98
     purpoſe
    0.98
     Monfieur
    0.98
     myſelf
    0.97
     Federated
    0.95
    Act Density 0.004%

    No Known Activations