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

    Neuronpedia

    INDEX
    Explanations

    words related to different groups of people (e.g., teens, developers, gamers) and their activities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.65
     Territories
    -0.63
     Settlement
    -0.63
     srfAttach
    -0.63
    inventoryQuantity
    -0.62
     Humane
    -0.62
    Accessory
    -0.61
     Reading
    -0.61
     Houth
    -0.59
    EngineDebug
    -0.59
    POSITIVE LOGITS
     alike
    0.82
     prefer
    0.81
     hesitate
    0.81
    hops
    0.76
     surveyed
    0.75
    etsy
    0.73
     polled
    0.73
     opted
    0.73
     aspire
    0.70
     agree
    0.69
    Act Density 0.281%

    No Known Activations