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

    Neuronpedia

    INDEX
    Explanations

    quantities or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    instances of the end of text markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respons
    -0.60
    _.
    -0.53
    pled
    -0.53
    ?,
    -0.53
     toget
    -0.52
     versa
    -0.52
    sic
    -0.52
     thereafter
    -0.52
     destro
    -0.51
     thereof
    -0.51
    POSITIVE LOGITS
     SHARES
    0.72
     Introduction
    0.72
     Summary
    0.72
     Transcript
    0.70
    reetings
    0.68
     Description
    0.67
     Calculator
    0.67
     Overview
    0.67
     Definitions
    0.66
     Recipe
    0.65
    Act Density 0.320%

    No Known Activations