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

    Neuronpedia

    INDEX
    Explanations

    phrases related to abstract concepts such as humor, purpose, and fulfillment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "sense."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.90
    sites
    -0.82
    ansas
    -0.74
    STER
    -0.70
    esan
    -0.70
    heid
    -0.69
    ials
    -0.67
    users
    -0.66
    iaries
    -0.66
    nr
    -0.65
    POSITIVE LOGITS
     urgency
    1.32
     humor
    1.07
     accomplishment
    1.07
     humour
    1.06
     entitlement
    1.06
     superiority
    1.00
     guilt
    0.94
     awe
    0.94
     injustice
    0.94
     dé
    0.93
    Act Density 0.070%

    No Known Activations