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

    Neuronpedia

    INDEX
    Explanations

    economic and financial terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.77
     unus
    -0.76
     unob
    -0.74
     allowance
    -0.73
     pit
    -0.73
     optional
    -0.72
     hatch
    -0.69
     whis
    -0.69
     alley
    -0.69
     warr
    -0.68
    POSITIVE LOGITS
     Firstly
    1.61
     Especially
    1.51
     Whereas
    1.47
     Particularly
    1.41
     Specifically
    1.38
     Whether
    1.34
     Suppose
    1.32
     Perhaps
    1.32
     Instead
    1.31
     Indeed
    1.30
    Act Density 2.631%

    No Known Activations