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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptors related to architectural features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sublist
    -0.16
    ÑĨвеÑĤ
    -0.15
    å²Ĺ
    -0.15
    oku
    -0.14
     relativ
    -0.14
     s
    -0.14
    à¹Īà¸Ńà¸ĩ
    -0.14
    chet
    -0.14
    Å¡ak
    -0.14
     Parks
    -0.13
    POSITIVE LOGITS
     ceiling
    0.54
     ceilings
    0.52
     Ceiling
    0.47
     поÑĤол
    0.42
     roof
    0.38
    ceil
    0.35
     overhead
    0.35
     ceil
    0.34
     vault
    0.31
    -ce
    0.31
    Act Density 0.108%

    No Known Activations