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

    Neuronpedia

    INDEX
    Explanations

    references to political figures, particularly presidents and governors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political leaders, specifically presidents and governors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTV
    -0.73
    INGTON
    -0.67
    Population
    -0.66
    Operation
    -0.66
     Territories
    -0.65
    Hur
    -0.65
     Palest
    -0.64
     Thing
    -0.63
     Boy
    -0.62
    LAN
    -0.61
    POSITIVE LOGITS
    hips
    1.62
    hip
    1.61
    paces
    1.19
    mith
    1.08
    ervatives
    1.01
    ettings
    0.98
    uits
    0.98
    htaking
    0.95
    creen
    0.94
    pace
    0.91
    Act Density 0.123%

    No Known Activations