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

    Neuronpedia

    INDEX
    Explanations

    information about potential consequences, impacts, and outcomes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ogie
    -1.16
    cipline
    -1.12
    otle
    -1.04
    chet
    -1.00
    car
    -0.99
    bows
    -0.97
    adays
    -0.96
     Label
    -0.94
    tein
    -0.94
    beard
    -0.94
    POSITIVE LOGITS
    ities
    1.36
    izons
    1.30
    ibilities
    1.20
     implications
    1.17
     usefulness
    1.17
     synerg
    1.11
     hazards
    1.10
     future
    1.09
     payoff
    1.08
     unintended
    1.08
    Act Density 1.015%

    No Known Activations