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

    Neuronpedia

    INDEX
    Explanations

    references to American concepts, values, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to American identity and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liga
    -0.89
    rator
    -0.82
    interstitial
    -0.81
    ikarp
    -0.81
    aler
    -0.80
    linger
    -0.78
    epad
    -0.78
    oscope
    -0.76
    isode
    -0.76
    pherd
    -0.74
    POSITIVE LOGITS
     institutions
    1.04
     ingenuity
    1.04
     attitudes
    1.00
     sensibilities
    0.99
     priorities
    0.99
     society
    0.98
     interests
    0.98
     supremacy
    0.98
     civilization
    0.98
     sovereignty
    0.98
    Act Density 0.307%

    No Known Activations