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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically focusing on names likely related to the same topic

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "Bevin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.98
    arers
    -0.68
     cropped
    -0.68
    awei
    -0.67
    erity
    -0.66
    lain
    -0.65
    bler
    -0.64
    spring
    -0.63
    steps
    -0.62
    akening
    -0.62
    POSITIVE LOGITS
    ces
    0.97
    eteen
    0.89
    warm
    0.88
    cent
    0.87
    eteenth
    0.86
    nings
    0.86
    jury
    0.84
    idia
    0.83
    iti
    0.82
    nen
    0.82
    Act Density 0.019%

    No Known Activations