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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts

    oai_token-act-pair · gpt-3.5-turbo

    prices and monetary values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Intervention
    -0.74
     Gors
    -0.73
     Tall
    -0.71
     Tid
    -0.68
     Schn
    -0.68
     Reborn
    -0.68
     Referred
    -0.67
     constitu
    -0.67
     Nare
    -0.65
     exerc
    -0.64
    POSITIVE LOGITS
    $$
    1.33
    $$$$
    1.30
    USD
    1.00
    ©¶æ¥µ
    0.95
    HOME
    0.95
    -$
    0.93
    100
    0.90
    GOP
    0.90
    false
    0.90
    AUD
    0.88
    Act Density 0.079%

    No Known Activations