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

    Neuronpedia

    INDEX
    Explanations

    references to ceilings or ceiling-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typelib
    -0.57
    Prior
    -0.55
     Prior
    -0.52
    qai
    -0.49
     Adirond
    -0.46
     Swain
    -0.46
     Pal
    -0.45
    =[],
    -0.45
    кра
    -0.44
    setminus
    -0.43
    POSITIVE LOGITS
     ceiling
    1.57
    ceiling
    1.45
     ceilings
    1.40
     Ceiling
    1.38
    Ceiling
    1.31
     plafond
    1.04
     Decken
    0.91
     Decke
    0.78
    Пото
    0.77
    +#+#
    0.77
    Act Density 0.081%

    No Known Activations