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

    Neuronpedia

    INDEX
    Explanations

    words related to sharp objects or tools

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, primarily names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amed
    -0.79
    isites
    -0.64
    aciously
    -0.64
    chest
    -0.63
    ipple
    -0.62
     psychiat
    -0.62
    inen
    -0.61
    aming
    -0.61
    nings
    -0.61
    IELD
    -0.60
    POSITIVE LOGITS
    rouch
    0.85
    ancel
    0.75
    ursor
    0.74
    urrency
    0.74
    pillar
    0.73
    nces
    0.73
    rossover
    0.70
    ursive
    0.70
    aught
    0.68
    urses
    0.68
    Act Density 0.325%

    No Known Activations