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

    Neuronpedia

    INDEX
    Explanations

    phrases related to business agreements and deals

    oai_token-act-pair · gpt-3.5-turbo

    references to contracts and agreements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rebell
    -0.67
    ometimes
    -0.66
    ocaust
    -0.66
    answered
    -0.65
    iris
    -0.62
    inas
    -0.61
    acists
    -0.61
     dictators
    -0.57
    licks
    -0.57
     wakes
    -0.57
    POSITIVE LOGITS
     memorandum
    0.94
     dated
    0.85
     agreement
    0.82
     totaling
    0.81
     worth
    0.81
     to
    0.81
     for
    0.80
     authorizing
    0.79
     whereby
    0.77
    itled
    0.77
    Act Density 0.219%

    No Known Activations