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

    Neuronpedia

    INDEX
    Explanations

    words related to authority and certainty

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "absolute" as a descriptor or qualifier

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.89
    actionDate
    -0.88
    nan
    -0.85
    enegger
    -0.83
    anners
    -0.82
    jet
    -0.81
    bucks
    -0.80
    pocket
    -0.78
    neys
    -0.77
    ACP
    -0.77
    POSITIVE LOGITS
     monarchy
    1.10
     beginners
    0.88
     majority
    0.87
     monarch
    0.85
     positioning
    0.80
     importance
    0.80
     domination
    0.80
     relaxation
    0.78
     humidity
    0.78
     priority
    0.76
    Act Density 0.015%

    No Known Activations