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

    Neuronpedia

    INDEX
    Explanations

    proper names or surnames of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.78
    worldly
    -0.68
     Croatian
    -0.66
     migr
    -0.66
     Bulgar
    -0.66
    isite
    -0.66
    ursday
    -0.63
     deduction
    -0.62
     Italians
    -0.62
    drm
    -0.62
    POSITIVE LOGITS
    lee
    0.81
    SHA
    0.78
    igham
    0.74
    ney
    0.74
    lein
    0.70
    KY
    0.70
    rand
    0.68
    houn
    0.66
    ATCH
    0.66
    inelli
    0.66
    Act Density 0.113%

    No Known Activations