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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of legal or governmental powers

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or governmental powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    algia
    -0.75
    antz
    -0.75
    Gil
    -0.74
     Mell
    -0.73
    yrinth
    -0.69
    riad
    -0.68
     Dwell
    -0.68
    eday
    -0.66
     Alto
    -0.64
     Sins
    -0.63
    POSITIVE LOGITS
     delegated
    1.06
     conferred
    1.05
     powers
    1.05
     vested
    0.97
     granted
    0.92
     exerc
    0.86
    Reviewer
    0.83
     unchecked
    0.83
    Ability
    0.82
     Powers
    0.80
    Act Density 0.038%

    No Known Activations