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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, especially related to political figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lain
    -1.03
    Reviewed
    -1.02
     crawl
    -1.01
    endant
    -0.97
    pmwiki
    -0.96
    mble
    -0.94
    igslist
    -0.94
    places
    -0.94
    ioned
    -0.91
    anwhile
    -0.89
    POSITIVE LOGITS
     Orwell
    1.25
     Lucas
    1.13
     Soros
    1.09
     Wallace
    1.07
     Zimmerman
    1.06
     Clo
    1.06
    STON
    1.05
     RR
    1.05
     Thor
    1.01
     Bush
    1.00
    Act Density 0.773%

    No Known Activations