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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political power and authority

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    algia
    -0.81
     Mell
    -0.73
    eday
    -0.73
    yrinth
    -0.72
    Gil
    -0.72
     Sins
    -0.72
    antz
    -0.71
    atari
    -0.70
    eros
    -0.69
     Dwell
    -0.68
    POSITIVE LOGITS
     conferred
    1.18
     delegated
    1.16
     powers
    1.12
     vested
    1.04
     granted
    0.99
     exerc
    0.92
     bestowed
    0.84
    Ability
    0.83
     wielded
    0.83
     Powers
    0.82
    Act Density 0.030%

    No Known Activations