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

    Neuronpedia

    INDEX
    Explanations

    references to sovereign entities or authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sovereignty and sovereign entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ograp
    -0.82
    orah
    -0.82
    chel
    -0.77
    xxxxxxxx
    -0.77
     McGee
    -0.73
    OUT
    -0.70
    ucket
    -0.68
    DERR
    -0.66
    UNCH
    -0.66
    _>
    -0.66
    POSITIVE LOGITS
     immunity
    0.92
     sovereign
    0.81
    ignty
    0.79
     decree
    0.76
    s
    0.75
    urally
    0.73
     Instruments
    0.71
     monarch
    0.70
     debt
    0.70
    sum
    0.69
    Act Density 0.030%

    No Known Activations