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

    Neuronpedia

    INDEX
    Explanations

    monetary values or references to money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tid
    -0.83
     Halls
    -0.69
     Sne
    -0.68
     Nights
    -0.67
     Reborn
    -0.67
     Det
    -0.65
     Tall
    -0.65
     Dare
    -0.65
     Recomm
    -0.64
     Hearts
    -0.64
    POSITIVE LOGITS
    300
    1.18
    $$
    1.14
    100
    1.14
    200
    1.11
    400
    1.09
    500
    1.06
    600
    1.04
    800
    1.03
    150
    1.03
    900
    1.00
    Act Density 0.049%

    No Known Activations