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

    Neuronpedia

    INDEX
    Explanations

    layout-related attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollen
    -0.20
    ormal
    -0.17
    å½¹
    -0.15
    ãĥĥãĥĦ
    -0.15
    eden
    -0.15
     Už
    -0.15
    nf
    -0.15
     seni
    -0.14
    ea
    -0.14
    arsers
    -0.14
    POSITIVE LOGITS
    asan
    0.16
     Strat
    0.15
     wow
    0.15
    BUM
    0.15
    ots
    0.14
     tap
    0.14
    otron
    0.14
     Food
    0.14
     food
    0.14
     comple
    0.14
    Act Density 0.012%

    No Known Activations