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

    Neuronpedia

    INDEX
    Explanations

    coding-related terms and phrases, particularly related to programming languages and instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     indestru
    -0.77
     depic
    -0.75
     shenan
    -0.74
     contex
    -0.74
     sophistic
    -0.68
     viciss
    -0.68
     disambigu
    -0.67
     wikihow
    -0.67
     racon
    -0.67
     berea
    -0.66
    POSITIVE LOGITS
     programming
    1.40
     Programming
    1.21
    programming
    1.18
    Programming
    1.16
     programmer
    1.03
     programmers
    0.98
     programmed
    0.92
    programmed
    0.88
     program
    0.87
     PROGRAM
    0.87
    Act Density 0.054%

    No Known Activations