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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discretionary authority and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idal
    -0.15
    getc
    -0.15
    otland
    -0.14
    REDENTIAL
    -0.14
    bourg
    -0.14
     Sanayi
    -0.14
    γά
    -0.14
     Lodge
    -0.14
    боÑĤ
    -0.14
    æıı
    -0.13
    POSITIVE LOGITS
     subjective
    0.43
     personal
    0.39
     discretion
    0.39
     opinion
    0.33
    personal
    0.32
     choice
    0.31
     Personal
    0.28
     judgment
    0.27
    Personal
    0.27
     preference
    0.27
    Act Density 0.207%

    No Known Activations