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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific items or activities in a specific event or gathering

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     poichè
    -1.23
     alkoh
    -1.15
     kosme
    -1.12
     kön
    -1.12
     poliuret
    -1.08
     keramik
    -1.07
     perciò
    -1.06
     vuol
    -1.06
     silikon
    -1.05
     protokol
    -1.03
    POSITIVE LOGITS
     etc
    1.54
    etc
    1.36
     Etc
    1.07
     whatnot
    1.04
     ect
    0.94
     anything
    0.88
     even
    0.87
     whatever
    0.86
    Etc
    0.85
    等等
    0.77
    Act Density 0.259%

    No Known Activations