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

    Neuronpedia

    INDEX
    Explanations

    terms related to modular and upgradeable design features in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iros
    -0.15
    yro
    -0.15
    cts
    -0.15
     stabilized
    -0.14
    iesel
    -0.14
     stabilization
    -0.14
     íĻķìĭ¤
    -0.14
     trustworthy
    -0.13
    397
    -0.13
     Bou
    -0.13
    POSITIVE LOGITS
     exchange
    0.21
     exchanges
    0.19
     interchange
    0.18
     changing
    0.18
     exchanging
    0.18
     Changing
    0.18
    åį
    0.17
     interchangeable
    0.17
    à¹Ģà¸Ľà¸¥
    0.17
     easily
    0.17
    Act Density 0.141%

    No Known Activations