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

    Neuronpedia

    INDEX
    Explanations

    information related to pricing, dates, and terms in a text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.68
    Console
    -0.67
    ulner
    -0.66
    soc
    -0.64
    xit
    -0.62
    esides
    -0.61
    Switch
    -0.60
    oppable
    -0.58
     nevertheless
    -0.58
    XT
    -0.58
    POSITIVE LOGITS
     Schumer
    0.61
     Roosevelt
    0.60
     ordering
    0.56
     generous
    0.55
     comma
    0.55
    agraph
    0.52
     Dickinson
    0.52
     mandatory
    0.51
     Rue
    0.51
     Shaw
    0.50
    Act Density 0.240%

    No Known Activations