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

    Neuronpedia

    INDEX
    Explanations

    numbers related to dates and quantities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     in
    -0.65
     a
    -0.65
     to
    -0.63
     clearness
    -0.63
     he
    -0.60
     an
    -0.60
     at
    -0.60
     
    -0.59
     non
    -0.59
     normal
    -0.59
    POSITIVE LOGITS
     alkoh
    2.15
     makro
    2.12
     antik
    2.03
     silikon
    2.03
     kosme
    2.02
     karton
    2.00
     kask
    1.99
     keramik
    1.98
     elek
    1.94
     plak
    1.93
    Act Density 0.087%

    No Known Activations