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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically focusing on names like "Alberto" and "Enrique"

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bucks
    -0.76
    bread
    -0.75
    sylv
    -0.71
    fare
    -0.70
    wich
    -0.70
    child
    -0.68
    wig
    -0.66
    hum
    -0.66
    ears
    -0.66
    Minnesota
    -0.65
    POSITIVE LOGITS
     Enrique
    1.30
     Paulo
    1.16
     Gomez
    1.11
     Alonso
    1.10
     Antonio
    1.06
     Ramos
    1.05
    berto
    1.05
     Alberto
    1.04
     José
    1.03
     Fernandez
    1.03
    Act Density 0.016%

    No Known Activations