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

    Neuronpedia

    INDEX
    Explanations

    references to retrieving valuable items or completing missions

    oai_token-act-pair · gpt-3.5-turbo

    references to quests or missions involving retrieval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    occup
    -0.82
    allel
    -0.78
    axis
    -0.78
    paced
    -0.73
    both
    -0.68
    annels
    -0.68
     Atkinson
    -0.68
    athetic
    -0.68
    stand
    -0.67
    intensive
    -0.67
    POSITIVE LOGITS
     treasures
    1.70
     treasure
    1.59
     priceless
    1.58
     secrets
    1.41
     riches
    1.37
     relics
    1.37
     jewels
    1.32
     goodies
    1.32
     artifacts
    1.31
     gems
    1.30
    Act Density 0.656%

    No Known Activations