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

    Neuronpedia

    INDEX
    Explanations

    mentions of large amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts or financial figures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exerc
    -0.79
     Sed
    -0.72
     Redd
    -0.71
     Tid
    -0.68
     Tall
    -0.68
     pronounce
    -0.67
     Halls
    -0.67
     metab
    -0.67
     Valent
    -0.67
     Dod
    -0.67
    POSITIVE LOGITS
    100
    1.27
    150
    1.23
    500
    1.21
    300
    1.21
    250
    1.21
    200
    1.20
    1
    1.18
    400
    1.17
    $$
    1.15
    5
    1.15
    Act Density 0.088%

    No Known Activations