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

    Neuronpedia

    INDEX
    Explanations

    numbers and verbs indicating action

    oai_token-act-pair · gpt-3.5-turbo

    actions related to formal processes or transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heid
    -0.68
    erity
    -0.67
    inventoryQuantity
    -0.57
    bral
    -0.56
    ouf
    -0.54
     ze
    -0.54
    feeding
    -0.54
     humility
    -0.54
    isdom
    -0.54
     Anger
    -0.54
    POSITIVE LOGITS
     apiece
    1.20
     annually
    1.00
     worldwide
    0.99
     consecut
    0.98
     globally
    0.94
     nationwide
    0.93
     respectively
    0.91
     throughout
    0.90
     collectively
    0.90
     simultaneously
    0.89
    Act Density 0.311%

    No Known Activations