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

    Neuronpedia

    INDEX
    Explanations

    the names of specific government officials

    oai_token-act-pair · gpt-3.5-turbo

    names of government officials and their mentions in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Avalon
    -0.67
     Jagu
    -0.66
    ¥µ
    -0.64
    itar
    -0.63
     Betty
    -0.63
     Sheep
    -0.62
     Pyr
    -0.62
     Babe
    -0.61
     Dominion
    -0.61
     Proposition
    -0.60
    POSITIVE LOGITS
     briefed
    1.06
     memos
    0.92
     aide
    0.91
     oversaw
    0.90
     briefings
    0.89
     testified
    0.86
     resigned
    0.84
     chaired
    0.83
     Jinping
    0.82
    uchin
    0.81
    Act Density 0.128%

    No Known Activations