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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns or names related to monetary transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and entities involved in transactions or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.76
    execute
    -0.68
    linger
    -0.65
    isf
    -0.64
    notations
    -0.62
    iating
    -0.62
    éĥ
    -0.62
    sis
    -0.62
    enabled
    -0.61
    speak
    -0.60
    POSITIVE LOGITS
     something
    0.93
     billions
    0.90
     money
    0.87
     $
    0.84
     Rs
    0.83
     plenty
    0.81
     peanuts
    0.79
     £
    0.79
     anything
    0.78
     dearly
    0.78
    Act Density 0.205%

    No Known Activations