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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or phrases related to individuals or places, potentially with a pattern of "az" followed by a number varying from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    the name "Az" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kraken
    -0.67
     Fargo
    -0.64
    ãĤ©
    -0.64
     foremost
    -0.63
     Towns
    -0.63
     Kepler
    -0.63
     Kardashian
    -0.63
     Seah
    -0.62
     Impossible
    -0.62
     proportional
    -0.59
    POSITIVE LOGITS
    az
    1.10
    ombie
    1.08
    azel
    1.00
    eez
    0.98
    awa
    0.98
    quez
    0.97
    aza
    0.95
    ahar
    0.94
    hou
    0.94
    iah
    0.94
    Act Density 0.012%

    No Known Activations