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

    Neuronpedia

    INDEX
    Explanations

    keywords related to taxes and financial matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osw
    -0.79
     Jenner
    -0.72
    Ò
    -0.71
     Ange
    -0.70
    theless
    -0.70
     Watts
    -0.69
     Sisters
    -0.68
     Wond
    -0.67
     Lyon
    -0.66
     Jem
    -0.66
    POSITIVE LOGITS
    payer
    1.40
    onomy
    1.29
    onomic
    1.17
    payers
    1.13
    onom
    1.12
    paying
    0.99
     levied
    0.98
     collectors
    0.94
     evasion
    0.90
     payable
    0.89
    Act Density 0.505%

    No Known Activations