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

    Neuronpedia

    INDEX
    Explanations

    references to innovative architectural features and construction techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еле
    -0.15
    illo
    -0.15
    imitives
    -0.14
    ÙĪاء
    -0.14
     fused
    -0.14
    /browse
    -0.14
    hton
    -0.13
    prob
    -0.13
    кеÑĤ
    -0.13
    -lfs
    -0.13
    POSITIVE LOGITS
     rains
    0.24
     facade
    0.22
     panels
    0.22
     faç
    0.21
     Reyn
    0.20
    \Modules
    0.19
     curtain
    0.19
     Panels
    0.19
     cl
    0.19
     finish
    0.19
    Act Density 0.042%

    No Known Activations