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

    Neuronpedia

    INDEX
    Explanations

    references to the word "polished" or similar variations describing a smooth and refined surface or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.18
    azine
    -0.16
    anker
    -0.16
    liner
    -0.15
    iles
    -0.15
    ungal
    -0.15
    ually
    -0.14
    amples
    -0.14
    ึ
    -0.14
    slave
    -0.14
    POSITIVE LOGITS
    ych
    0.18
    enta
    0.17
    ynomials
    0.16
    ITICAL
    0.15
    arity
    0.15
     Dome
    0.15
    mav
    0.15
    oin
    0.15
    astr
    0.15
    r
    0.15
    Act Density 0.031%

    No Known Activations