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

    Neuronpedia

    INDEX
    Explanations

    references to prestigious awards or prizes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    folk
    -0.70
    olson
    -0.65
     aber
    -0.64
    cos
    -0.64
     lear
    -0.63
    fun
    -0.62
     Anon
    -0.61
     WARN
    -0.61
    auga
    -0.60
     Uz
    -0.60
    POSITIVE LOGITS
    Winner
    1.00
     Award
    0.97
     Winner
    0.97
     Winners
    0.97
     winner
    0.97
     awarded
    0.97
     Prize
    0.95
    winning
    0.92
    ®
    0.91
     laureate
    0.90
    Act Density 0.037%

    No Known Activations