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

    Neuronpedia

    INDEX
    Explanations

    non-financial terms or concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.97
     Oaks
    -0.75
     Grind
    -0.74
     Grill
    -0.73
     Showdown
    -0.73
     Spoon
    -0.70
     Dug
    -0.68
     Franks
    -0.68
     Banner
    -0.68
     Dew
    -0.65
    POSITIVE LOGITS
    linear
    1.21
    chal
    1.16
    profit
    1.15
    lethal
    1.15
    verbal
    1.14
    zero
    1.12
    fiction
    1.12
    technical
    1.12
    existent
    1.11
    stop
    1.08
    Act Density 0.810%

    No Known Activations