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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics and government

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" used in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amps
    -0.73
     Jagu
    -0.72
    aires
    -0.72
    antry
    -0.72
    anism
    -0.69
    Contents
    -0.69
     eg
    -0.68
    ittens
    -0.67
    ['
    -0.66
    opers
    -0.64
    POSITIVE LOGITS
    cknowled
    1.04
     slew
    1.02
     handful
    0.99
     landmark
    0.95
     lengthy
    0.94
     dozen
    0.93
     plethora
    0.92
     recent
    0.91
     whopping
    0.90
     sizable
    0.90
    Act Density 0.769%

    No Known Activations