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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific individuals named "Kade."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ade" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipeg
    -0.83
    urally
    -0.75
     nep
    -0.75
    urers
    -0.73
    igration
    -0.68
    ilogy
    -0.65
    enegger
    -0.64
    ullivan
    -0.64
     compr
    -0.64
     Kaufman
    -0.64
    POSITIVE LOGITS
    lled
    0.90
    hyde
    0.80
    lla
    0.77
    utic
    0.77
    ildo
    0.76
    pee
    0.76
    lda
    0.75
    ع
    0.75
    aways
    0.74
    cade
    0.72
    Act Density 0.019%

    No Known Activations