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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and political matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozyg
    -0.69
    aido
    -0.63
    soDeliveryDate
    -0.62
     varies
    -0.62
     differs
    -0.61
     Surprise
    -0.61
     swapped
    -0.60
    lav
    -0.59
     Eater
    -0.59
     sightings
    -0.58
    POSITIVE LOGITS
     credibility
    0.95
     altogether
    0.91
     democratic
    0.85
     cohesion
    0.82
     integrity
    0.82
     democracy
    0.81
     livelihood
    0.81
     legitimacy
    0.80
     cherished
    0.80
     orthodoxy
    0.79
    Act Density 0.514%

    No Known Activations