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

    Neuronpedia

    INDEX
    Explanations

    references to sovereign entities or conditions of authority and power

    oai_token-act-pair · gpt-3.5-turbo

    references to sovereignty and governing authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNCH
    -0.87
    OUT
    -0.79
    orah
    -0.74
    xxxxxxxx
    -0.73
    ACK
    -0.73
     McGee
    -0.73
    tein
    -0.72
     Hopkins
    -0.71
    acha
    -0.70
    OST
    -0.68
    POSITIVE LOGITS
     immunity
    0.88
    s
    0.88
     sovereign
    0.85
    urally
    0.79
     decree
    0.78
    sburg
    0.76
     monarch
    0.75
    iazep
    0.74
     entity
    0.73
    ignty
    0.73
    Act Density 0.017%

    No Known Activations