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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority and control in governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.16
    usch
    -0.14
    ä¸į足
    -0.14
    ив
    -0.14
    Ư
    -0.14
    ой
    -0.14
    ivas
    -0.14
     Preconditions
    -0.13
    ä¹ĺ
    -0.13
    ä¾
    -0.13
    POSITIVE LOGITS
     say
    0.34
     authority
    0.33
     veto
    0.31
     sway
    0.29
     influence
    0.29
    say
    0.29
     responsibility
    0.28
     Say
    0.27
    Say
    0.27
     jurisdiction
    0.26
    Act Density 0.153%

    No Known Activations