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

    Neuronpedia

    INDEX
    Explanations

    words related to legal proceedings and political figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to pressure and legal rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ended
    -0.66
    estamp
    -0.62
     belonged
    -0.61
     ancestor
    -0.59
     ..."
    -0.59
     THEN
    -0.58
     ||
    -0.56
     depended
    -0.56
     Tycoon
    -0.56
     1932
    -0.56
    POSITIVE LOGITS
     lately
    1.04
     increasingly
    0.97
     resurg
    0.83
     initiatives
    0.78
     lobbying
    0.77
     controversies
    0.75
     concerted
    0.73
     increasing
    0.72
     steadily
    0.72
     burgeoning
    0.71
    Act Density 1.091%

    No Known Activations