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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eals
    -0.69
    omorphic
    -0.68
    Plex
    -0.68
    actionDate
    -0.66
    âĸ¬
    -0.65
     Loaded
    -0.65
    pection
    -0.65
    otaur
    -0.65
     skelet
    -0.64
    omorph
    -0.62
    POSITIVE LOGITS
    oglu
    1.00
     Jr
    0.94
     Sr
    0.94
    ensis
    0.91
    ÄŁ
    0.88
     III
    0.87
    wu
    0.85
    Äĩ
    0.84
    ouf
    0.83
    yan
    0.83
    Act Density 0.266%

    No Known Activations