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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals throughout the document

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and significant identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.63
    idth
    -0.61
    cribed
    -0.59
    į
    -0.56
    %]
    -0.56
    ghai
    -0.55
    erial
    -0.54
    ?]
    -0.53
    emet
    -0.52
    gew
    -0.51
    POSITIVE LOGITS
     Voting
    0.54
     Advis
    0.54
    ÃŃs
    0.53
    iller
    0.50
    's
    0.48
     portfolios
    0.48
     advisors
    0.48
     Enterprise
    0.48
     personally
    0.48
     Sovereign
    0.47
    Act Density 0.719%

    No Known Activations