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

    Neuronpedia

    INDEX
    Explanations

    steps in a technical procedure

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    azo
    -0.67
    atan
    -0.66
    etimes
    -0.66
     passer
    -0.65
    athered
    -0.65
     estranged
    -0.65
     minded
    -0.63
    checked
    -0.63
     womb
    -0.61
     institution
    -0.61
    POSITIVE LOGITS
     Conclusion
    0.90
    :{
    0.88
    :]
    0.87
     Procedure
    0.79
     Functions
    0.75
     Description
    0.75
    :
    0.74
     onwards
    0.74
     Introduction
    0.72
     Problem
    0.72
    Act Density 0.048%

    No Known Activations