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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or locators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    child
    -0.84
    deen
    -0.72
    manship
    -0.72
    thing
    -0.66
    uyomi
    -0.66
    PDATE
    -0.64
     Duchess
    -0.64
    boarding
    -0.64
    board
    -0.61
    200000
    -0.61
    POSITIVE LOGITS
    atell
    1.11
    ator
    1.05
    abulary
    1.00
    ally
    0.99
    ocity
    0.98
    alf
    0.92
    ution
    0.91
    ators
    0.89
    ational
    0.89
    uti
    0.89
    Act Density 0.031%

    No Known Activations