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

    Neuronpedia

    INDEX
    Explanations

    keywords related to political events and international relations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.72
    Express
    -0.72
     derog
    -0.67
     Dynamics
    -0.61
    BT
    -0.58
    NEY
    -0.58
    ffen
    -0.57
     Definition
    -0.54
     deeds
    -0.54
     Puzzles
    -0.52
    POSITIVE LOGITS
     dozen
    0.95
     eighty
    0.93
     450
    0.89
    dozen
    0.88
     200
    0.88
     80
    0.87
     400
    0.86
     seventy
    0.86
     850
    0.86
     700
    0.84
    Act Density 1.405%

    No Known Activations