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

    Neuronpedia

    INDEX
    Explanations

    terms related to American culture, values, politics, and history

    oai_token-act-pair · gpt-3.5-turbo

    references to American identity and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.84
    pots
    -0.82
    ÃŁ
    -0.82
    cffffcc
    -0.81
    aday
    -0.77
    rences
    -0.76
    hooting
    -0.75
    NB
    -0.74
    theless
    -0.72
    _>
    -0.72
    POSITIVE LOGITS
     Airlines
    1.08
     Idol
    1.04
     Samoa
    0.99
     Dream
    0.96
     Federation
    0.95
     Heritage
    0.92
     Legion
    0.92
     citizen
    0.91
     Revolution
    0.91
    ICAN
    0.89
    Act Density 0.051%

    No Known Activations