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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to political concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actory
    -0.91
    olen
    -0.86
    imates
    -0.80
    tered
    -0.80
    wered
    -0.79
    IER
    -0.78
     Cancel
    -0.77
    Customer
    -0.75
    xt
    -0.75
    cellent
    -0.75
    POSITIVE LOGITS
     correctness
    1.34
     clout
    0.95
     upheaval
    0.93
     affiliation
    0.89
     appoint
    0.87
     turmoil
    0.86
     affili
    0.86
     subdivision
    0.85
     affairs
    0.84
     pund
    0.84
    Act Density 0.041%

    No Known Activations