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

    Neuronpedia

    INDEX
    Explanations

    words related to leadership and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agra
    -0.66
    ensable
    -0.66
    awk
    -0.65
    iencies
    -0.64
    agon
    -0.64
     Pwr
    -0.64
    zl
    -0.64
    ogene
    -0.64
    berra
    -0.64
     tan
    -0.64
    POSITIVE LOGITS
    doms
    0.86
    boards
    0.84
    leader
    0.82
    pin
    0.80
    pins
    0.78
    esses
    0.78
    stration
    0.78
     negotiator
    0.75
     contender
    0.75
     frontrunner
    0.75
    Act Density 0.028%

    No Known Activations