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

    Neuronpedia

    INDEX
    Explanations

    mentions of positions such as "president" or specific positions held by individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     »>
    -0.71
     aen
    -0.70
     jacobs
    -0.67
     paula
    -0.65
     ricardo
    -0.64
     fta
    -0.63
     akku
    -0.63
     fua
    -0.63
     whiche
    -0.63
     thut
    -0.62
    POSITIVE LOGITS
     president
    1.44
    president
    1.34
     President
    1.31
    President
    1.27
     presidents
    1.25
     presidency
    1.18
     PRESIDENT
    1.08
     Presidents
    1.07
    PRESIDENT
    1.04
     presidential
    0.99
    Act Density 0.085%

    No Known Activations