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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Deputy"

    oai_token-act-pair · gpt-3.5-turbo

    references to deputy positions and their related duties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rock
    -0.65
     melting
    -0.64
     sweep
    -0.63
     bust
    -0.62
     scratching
    -0.62
    Rock
    -0.62
     cleaning
    -0.60
     feeding
    -0.59
     Sph
    -0.58
     exploration
    -0.57
    POSITIVE LOGITS
    uty
    4.58
    uties
    2.14
    oub
    1.02
    ischer
    1.02
     Duty
    0.95
    duty
    0.95
    ut
    0.93
    utive
    0.92
    uted
    0.88
    ilon
    0.87
    Act Density 0.015%

    No Known Activations