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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, likely related to specific names such as 'Dewhurst' and 'Dempsey'

    oai_token-act-pair · gpt-3.5-turbo

    references to an individual named Dewhurst

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.87
    ================================================================
    -0.78
    ning
    -0.77
    cil
    -0.74
    chest
    -0.73
    meal
    -0.67
    book
    -0.66
    teenth
    -0.65
    folios
    -0.64
    packing
    -0.64
    POSITIVE LOGITS
    inatory
    0.96
    anasia
    0.92
    ensional
    0.85
    inates
    0.80
    inately
    0.78
    inx
    0.78
    aneers
    0.77
    ayne
    0.74
    inators
    0.73
    yll
    0.72
    Act Density 0.071%

    No Known Activations