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

    Neuronpedia

    INDEX
    Explanations

    words related to stoicism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stoic" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordable
    -0.75
     Horizons
    -0.75
    UAL
    -0.72
    displayText
    -0.72
    ually
    -0.72
    URI
    -0.68
     Pathfinder
    -0.68
     Odyssey
    -0.67
    ATA
    -0.67
    URR
    -0.67
    POSITIVE LOGITS
    pper
    1.12
     sto
    1.06
    ppy
    1.05
    pped
    1.00
    pping
    0.97
    ppers
    0.96
    ops
    0.85
    ppings
    0.83
    ven
    0.80
    ffer
    0.79
    Act Density 0.012%

    No Known Activations