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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "one of," frequently indicating membership or classification within a larger group or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zeb
    -0.93
    anse
    -0.65
    lees
    -0.63
    matter
    -0.62
    ption
    -0.60
    au
    -0.59
    %:
    -0.58
    IRE
    -0.58
    istine
    -0.58
    claimed
    -0.57
    POSITIVE LOGITS
     several
    1.16
     dozens
    1.05
     few
    1.03
     four
    1.02
     five
    1.02
     many
    1.02
     seven
    1.00
     three
    1.00
     eight
    0.99
     nine
    0.99
    Act Density 0.056%

    No Known Activations