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

    Neuronpedia

    INDEX
    Explanations

    mentions of institutions or power structures

    oai_token-act-pair · gpt-3.5-turbo

    references to the political establishment and its influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    range
    -0.83
    tnc
    -0.78
    cific
    -0.76
     Marketable
    -0.76
    brid
    -0.75
    spell
    -0.72
    ranged
    -0.72
    Film
    -0.70
    Cooldown
    -0.70
     Nieto
    -0.70
    POSITIVE LOGITS
    ablishment
    1.18
     establishment
    0.99
     Establishment
    0.93
     establishments
    0.85
     conservatism
    0.81
     affili
    0.78
    itutes
    0.75
     elites
    0.74
    eers
    0.74
     apparatus
    0.71
    Act Density 0.014%

    No Known Activations