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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal documents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -8.89
     increa
    -8.84
     inev
    -8.41
     impra
    -8.26
     disagre
    -8.25
     affor
    -8.20
     depic
    -8.13
     volunte
    -8.13
     encomp
    -8.05
     shenan
    -8.05
    POSITIVE LOGITS
    <bos>
    13.34
     Paglinawan
    2.47
     betweenstory
    2.36
     Walkover
    2.27
    RegressionTest
    2.25
    Autoritní
    2.24
     Italijani
    2.23
    はじめに
    2.22
    ↵
    2.21
    Panamoan
    2.18
    Act Density 0.071%

    No Known Activations