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

    Neuronpedia

    INDEX
    Explanations

    politically related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of political promises or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Craigslist
    -0.75
     hog
    -0.73
     Pse
    -0.72
     Sph
    -0.69
     OW
    -0.67
     trivia
    -0.66
     Hedge
    -0.66
     lol
    -0.66
     pseud
    -0.65
     Hubbard
    -0.64
    POSITIVE LOGITS
     readiness
    1.03
     humanitarian
    0.96
     strengthening
    0.93
    ilateral
    0.92
    ourage
    0.91
     diplomacy
    0.91
     honour
    0.87
     deepening
    0.87
     respects
    0.85
    ouble
    0.85
    Act Density 0.736%

    No Known Activations