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

    Neuronpedia

    INDEX
    Explanations

    information related to weight measurement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     galo
    -1.13
     lele
    -1.12
     kram
    -1.12
     silikon
    -1.11
     makro
    -1.10
     frans
    -1.09
     wien
    -1.09
     meis
    -1.09
     milano
    -1.08
     pira
    -1.08
    POSITIVE LOGITS
     approximately
    0.77
     roughly
    0.70
     Até
    0.65
     Embora
    0.64
     Apesar
    0.64
     approx
    0.63
     shayari
    0.62
     Enquanto
    0.61
     absl
    0.61
     Muito
    0.61
    Act Density 0.271%

    No Known Activations