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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and government activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    apest
    -0.80
     Seller
    -0.76
    taboola
    -0.74
    pert
    -0.74
    flush
    -0.73
    izers
    -0.73
    spir
    -0.71
    selves
    -0.70
    esta
    -0.68
    vo
    -0.67
    POSITIVE LOGITS
     Academy
    1.15
     colonel
    1.06
     Corps
    1.06
     Reserve
    1.06
     stationed
    0.99
     Awakens
    0.97
     Base
    0.91
     Command
    0.88
     barracks
    0.87
     Museum
    0.86
    Act Density 0.046%

    No Known Activations