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

    Neuronpedia

    INDEX
    Explanations

    topics related to technology, innovation, and research in various industries

    oai_token-act-pair · gpt-3.5-turbo

    topics related to various areas of expertise and specialized knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predetermined
    -0.82
    same
    -0.78
     rotating
    -0.71
     redeem
    -0.70
     equal
    -0.70
     limb
    -0.68
     flesh
    -0.68
     claw
    -0.67
     slog
    -0.66
     resent
    -0.66
    POSITIVE LOGITS
     Basics
    1.48
     Matters
    1.46
     Tips
    1.33
     Advice
    1.33
     Techniques
    1.31
     Digest
    1.30
     Patterns
    1.30
     Lessons
    1.29
     Guide
    1.29
     Overview
    1.29
    Act Density 0.333%

    No Known Activations