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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and community discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     anecd
    -0.85
     remarkably
    -0.63
    ensibly
    -0.62
    uitive
    -0.59
    ometimes
    -0.57
    ggles
    -0.57
     intuitive
    -0.56
    entimes
    -0.55
     churn
    -0.55
    xtap
    -0.55
    POSITIVE LOGITS
     ASAP
    0.80
     ransom
    0.63
     apologise
    0.62
     repent
    0.60
     paternity
    0.58
    arations
    0.58
     extradition
    0.58
     incrim
    0.58
     £
    0.57
     repayment
    0.57
    Act Density 1.111%

    No Known Activations