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

    Neuronpedia

    INDEX
    Explanations

    linguistic patterns related to language translation or analysis

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to cultural or social identity, particularly those with linguistic variation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nen
    -0.84
     Kardashian
    -0.70
    abad
    -0.67
    oway
    -0.66
     AAP
    -0.64
     Higgins
    -0.62
    ney
    -0.60
    bek
    -0.60
    sha
    -0.60
    pick
    -0.59
    POSITIVE LOGITS
    issance
    1.21
    uthor
    1.20
    hedral
    1.09
    ñ
    1.08
    isance
    1.06
    ç
    1.03
    ire
    1.03
    BILITIES
    1.03
    ires
    0.97
    BILITY
    0.95
    Act Density 0.121%

    No Known Activations