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

    Neuronpedia

    INDEX
    Explanations

    political figures and government institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities and individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disappeared
    -0.83
     vanished
    -0.74
     died
    -0.71
     replaced
    -0.70
    Joined
    -0.62
     };
    -0.62
     PLUS
    -0.62
     crashed
    -0.62
     disappears
    -0.61
     inactive
    -0.60
    POSITIVE LOGITS
    erning
    0.96
     policymakers
    0.84
    antics
    0.79
     thinking
    0.76
     wondering
    0.76
     contemplating
    0.75
     puzzling
    0.74
     understandably
    0.74
     hesitate
    0.72
     puzz
    0.70
    Act Density 0.505%

    No Known Activations