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

    Neuronpedia

    INDEX
    Explanations

    phrases related to terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to terms or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oday
    -0.72
     mornings
    -0.67
     Tycoon
    -0.66
    psc
    -0.66
    zo
    -0.64
    icons
    -0.62
    heastern
    -0.62
     Borough
    -0.62
    burgh
    -0.60
    prep
    -0.58
    POSITIVE LOGITS
     service
    0.93
     reference
    0.88
     Reference
    0.84
     limitation
    0.83
     repayment
    0.83
     employment
    0.82
     surrender
    0.81
     engagement
    0.80
    payment
    0.79
     probation
    0.79
    Act Density 0.043%

    No Known Activations