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

    Neuronpedia

    INDEX
    Explanations

    mentions of interactions or relationships involving various individuals

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to articles or phrases describing relationships or encounters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.83
    inventoryQuantity
    -0.81
    oids
    -0.81
    ships
    -0.74
    isites
    -0.73
     engines
    -0.73
     portals
    -0.71
     indicators
    -0.70
    ģ«
    -0.70
     decks
    -0.70
    POSITIVE LOGITS
     woman
    1.22
     colleague
    1.19
     friend
    1.14
     classmate
    1.14
    unts
    1.08
     member
    1.06
     stranger
    1.04
     girl
    1.02
     prostitute
    1.02
     cowork
    1.02
    Act Density 0.250%

    No Known Activations