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

    Neuronpedia

    INDEX
    Explanations

    names related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Boris" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appra
    -0.70
     SOC
    -0.70
    College
    -0.68
     Native
    -0.68
     log
    -0.67
     Geek
    -0.65
    iary
    -0.65
    Ep
    -0.65
    collect
    -0.64
    gew
    -0.64
    POSITIVE LOGITS
     Boris
    3.58
    adiq
    2.12
     Giuliani
    1.68
    oris
    1.63
     Denis
    1.11
     Euros
    1.05
     Rudy
    1.04
     Zac
    1.03
     Tobias
    1.02
    imir
    0.99
    Act Density 0.045%

    No Known Activations