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

    Neuronpedia

    INDEX
    Explanations

    visual descriptions of spots or patches on surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agli
    -0.18
    edir
    -0.16
    loo
    -0.15
    AMS
    -0.15
     newPos
    -0.15
    midt
    -0.15
    undler
    -0.15
    JD
    -0.14
    oug
    -0.14
    uty
    -0.14
    POSITIVE LOGITS
    ãĥªãĥ¼ãĤº
    0.17
    ish
    0.17
     patches
    0.17
    åĦ¿
    0.15
    vice
    0.15
    kud
    0.15
     formation
    0.15
    åħĴ
    0.15
    .LayoutStyle
    0.14
     patch
    0.14
    Act Density 0.084%

    No Known Activations