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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "zero" in various contexts, particularly related to tolerance and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ystore
    -0.16
    yny
    -0.15
    bjerg
    -0.14
    agu
    -0.14
    gal
    -0.14
    ycastle
    -0.13
    ssel
    -0.13
     vua
    -0.13
    shape
    -0.13
    allery
    -0.13
    POSITIVE LOGITS
     tolerance
    0.33
    ing
    0.25
     gravity
    0.23
    -sum
    0.23
     tolerant
    0.23
    ed
    0.22
    /null
    0.22
    th
    0.22
     sum
    0.21
    eth
    0.21
    Act Density 0.012%

    No Known Activations