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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names likely expressing a specific person's name "Nunn"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names, and the word "loading."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PAX
    -0.94
     Esper
    -0.78
     AE
    -0.76
     Sierra
    -0.75
     Exile
    -0.75
     exile
    -0.73
    agon
    -0.72
     cou
    -0.71
    endez
    -0.69
     lands
    -0.69
    POSITIVE LOGITS
    unn
    2.52
     Rud
    1.37
     Loading
    1.20
    unny
    1.06
    actor
    1.05
    edi
    0.99
     Yam
    0.99
    rawn
    0.98
     Dunn
    0.95
    raud
    0.89
    Act Density 0.041%

    No Known Activations