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

    Neuronpedia

    INDEX
    Explanations

    UI component classes and layout structures within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĹ↵↵
    -0.17
    indow
    -0.16
     sobie
    -0.16
    lasses
    -0.15
    own
    -0.14
    /Common
    -0.14
    ycop
    -0.14
    ppo
    -0.14
    ispers
    -0.14
    rait
    -0.14
    POSITIVE LOGITS
    .TestTools
    0.15
     fur
    0.15
     Lah
    0.14
    ter
    0.14
    275
    0.14
     Vance
    0.14
     text
    0.14
    273
    0.14
    peater
    0.14
     z
    0.13
    Act Density 0.010%

    No Known Activations