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

    Neuronpedia

    INDEX
    Explanations

    mentions of emails and technical details or procedures in a formal context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eele
    -0.71
     AVG
    -0.68
     Cassidy
    -0.66
     Starr
    -0.64
     Cecil
    -0.61
     Witches
    -0.60
     KP
    -0.60
     OPEC
    -0.58
     Loll
    -0.58
     McCartney
    -0.58
    POSITIVE LOGITS
    mails
    1.35
    commerce
    1.35
    mail
    1.34
    cigarette
    1.24
    expression
    1.08
    cigarettes
    1.04
    ventures
    1.04
    Commerce
    1.03
    liquid
    1.01
    government
    0.98
    Act Density 0.020%

    No Known Activations