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

    Neuronpedia

    INDEX
    Explanations

    government-related terms and processes that require different levels of approval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government and legislative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cients
    -0.72
    achu
    -0.68
    iggurat
    -0.68
    ramid
    -0.67
    agame
    -0.67
    gdala
    -0.66
    undrum
    -0.64
    abase
    -0.64
    ient
    -0.63
     Puzzle
    -0.63
    POSITIVE LOGITS
     approval
    1.50
     intervention
    1.37
     scrutiny
    1.36
     supervision
    1.34
     permission
    1.32
     involvement
    1.31
     attention
    1.27
     assistance
    1.25
     authorization
    1.21
     sponsorship
    1.18
    Act Density 0.421%

    No Known Activations