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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with the ending "ien" or "iene"

    oai_token-act-pair · gpt-3.5-turbo

    references to certain suffixes, particularly those ending in "ien"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.90
    ramid
    -0.89
    rooms
    -0.73
    atform
    -0.72
    hematic
    -0.72
    Discussion
    -0.65
    tons
    -0.63
    abouts
    -0.63
     spaced
    -0.62
    tub
    -0.61
    POSITIVE LOGITS
    vironment
    1.09
    ews
    0.91
    cia
    0.89
    emy
    0.87
    lein
    0.80
    hao
    0.80
    eme
    0.80
    unciation
    0.80
    heim
    0.79
    venue
    0.79
    Act Density 0.012%

    No Known Activations