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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áÄį
    -0.13
     bmp
    -0.13
     Successfully
    -0.13
    erto
    -0.13
    ços
    -0.13
    anki
    -0.13
     Arial
    -0.12
    éĩİ
    -0.12
    azen
    -0.12
     unsuccessful
    -0.12
    POSITIVE LOGITS
     expose
    0.23
     exposing
    0.22
     declar
    0.22
     exposed
    0.22
     exposes
    0.21
     express
    0.20
     exposure
    0.20
     transparent
    0.20
     vend
    0.19
     laz
    0.19
    Act Density 0.065%

    No Known Activations