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

    Neuronpedia

    INDEX
    Explanations

    references to the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bably
    -0.84
    iosyn
    -0.76
    ovie
    -0.71
    sticks
    -0.66
    ezvous
    -0.66
    unci
    -0.66
    »Ĵ
    -0.65
    errors
    -0.64
    inately
    -0.64
    */(
    -0.63
    POSITIVE LOGITS
     Geological
    1.18
     Postal
    1.05
     Embassy
    1.00
     Dollar
    0.98
     Government
    0.94
     Army
    0.90
     Department
    0.89
     Patent
    0.88
     Treasury
    0.88
     Constitution
    0.86
    Act Density 0.051%

    No Known Activations