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

    Neuronpedia

    INDEX
    Explanations

    financial transaction-related terms and instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.21
    harmed
    -1.20
    solicited
    -1.06
    ⓧ
    -0.97
    compromising
    -0.82
    intelligible
    -0.81
    
    -0.80
    /**
    -0.77
    warran
    -0.76
    conditionally
    -0.70
    POSITIVE LOGITS
     Manufact
    1.34
     Minang
    1.33
     incess
    1.32
     bandung
    1.28
     maroc
    1.27
     lele
    1.26
     dises
    1.26
     laci
    1.25
     magis
    1.24
     applau
    1.23
    Act Density 0.086%

    No Known Activations