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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Alexander."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Alexander."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neys
    -0.78
    zee
    -0.76
    rers
    -0.74
    ears
    -0.74
    etc
    -0.73
    fare
    -0.70
    eling
    -0.67
    glers
    -0.67
    bing
    -0.66
    cheon
    -0.65
    POSITIVE LOGITS
     Luthor
    0.85
     Gust
    0.84
     Gaul
    0.81
    andr
    0.80
    opoulos
    0.78
     Hamilton
    0.78
    ander
    0.77
    iev
    0.76
     Payne
    0.76
     Berk
    0.76
    Act Density 0.037%

    No Known Activations