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

    Neuronpedia

    INDEX
    Explanations

    names of individuals in the fields of politics, sports, and entertainment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.87
    ramid
    -0.85
    uden
    -0.85
    otle
    -0.74
    urgy
    -0.73
    aris
    -0.72
    andise
    -0.72
    opping
    -0.71
    toe
    -0.70
    matic
    -0.69
    POSITIVE LOGITS
     colleague
    1.11
     president
    1.08
     comrade
    1.06
     employee
    1.05
     deputy
    1.05
     dictator
    1.04
     classmate
    1.02
     congressman
    1.02
     politician
    1.02
     member
    1.01
    Act Density 4.199%

    No Known Activations