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

    Neuronpedia

    INDEX
    Explanations

    common surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly related to people and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNE
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.60
    hower
    -0.58
    REF
    -0.57
     mun
    -0.56
    jun
    -0.55
    WARN
    -0.54
     Leilan
    -0.53
    uits
    -0.53
     Mub
    -0.52
    POSITIVE LOGITS
    yk
    0.68
    iversary
    0.57
    iod
    0.57
    til
    0.57
    Hol
    0.55
    lez
    0.55
    gat
    0.54
    rium
    0.53
    kov
    0.53
    otal
    0.52
    Act Density 0.505%

    No Known Activations