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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial amounts and numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.68
     Redemption
    -0.66
     hegemony
    -0.59
    ãĥ¤
    -0.59
     moderation
    -0.58
     aggression
    -0.58
     menace
    -0.57
    inventoryQuantity
    -0.57
    Delivery
    -0.56
     Ital
    -0.56
    POSITIVE LOGITS
    ourcing
    1.08
    paces
    0.94
    ourced
    0.92
    entimes
    0.89
    ousands
    0.88
    chool
    0.85
     upon
    0.84
     of
    0.84
     thousands
    0.83
     ILCS
    0.80
    Act Density 0.476%

    No Known Activations