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

    Neuronpedia

    INDEX
    Explanations

    mentions of political positions and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to "shadow" cabinet members or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urses
    -0.92
    ickr
    -0.82
    awaru
    -0.80
    olitan
    -0.79
    ktop
    -0.75
    orsi
    -0.74
    renheit
    -0.74
    anchester
    -0.73
    erto
    -0.71
    keye
    -0.70
    POSITIVE LOGITS
    moon
    0.93
     shadow
    0.84
     Shadow
    0.83
    shadow
    0.82
    runners
    0.81
    boxing
    0.79
    loo
    0.78
    dust
    0.76
    runner
    0.75
    busters
    0.75
    Act Density 0.013%

    No Known Activations