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

    Neuronpedia

    INDEX
    Explanations

    words related to power dynamics and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to political power dynamics and strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DERR
    -0.74
     learners
    -0.72
     Redd
    -0.72
     Osw
    -0.71
     crochet
    -0.68
     uploaded
    -0.68
     Sapp
    -0.67
     recy
    -0.66
     spaced
    -0.66
     filler
    -0.65
    POSITIVE LOGITS
    iances
    1.01
    ablishment
    0.95
    ocracy
    0.94
    Government
    0.93
    establishment
    0.90
    ente
    0.89
    itions
    0.89
    unta
    0.88
    appro
    0.88
     dictatorship
    0.87
    Act Density 0.331%

    No Known Activations