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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government and political activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vain
    -0.80
    terday
    -0.80
    ictions
    -0.68
     periphery
    -0.66
    itably
    -0.66
     routine
    -0.65
     flatt
    -0.65
     multit
    -0.65
     lumber
    -0.64
     masked
    -0.64
    POSITIVE LOGITS
     Day
    1.12
     Room
    1.05
     Order
    1.04
     Clause
    1.03
     Accountability
    1.02
     Department
    1.02
     Council
    1.01
     Manager
    1.00
     Service
    0.99
     Party
    0.99
    Act Density 2.023%

    No Known Activations