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

    Neuronpedia

    INDEX
    Explanations

    names of prominent figures in political and intelligence positions

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent political and intelligence figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jagu
    -0.74
    Ü
    -0.72
    drivers
    -0.71
    ulia
    -0.67
     convent
    -0.64
     Sheep
    -0.64
     Babe
    -0.63
    Els
    -0.63
     Craigslist
    -0.63
    Torrent
    -0.62
    POSITIVE LOGITS
     briefed
    1.45
     briefings
    1.13
     testified
    1.09
     briefing
    1.06
     reiterated
    1.06
     oversaw
    1.01
     chaired
    1.00
     warned
    1.00
     outlined
    0.98
     presided
    0.97
    Act Density 0.148%

    No Known Activations