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

    Neuronpedia

    INDEX
    Explanations

    terms related to structural characteristics and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     structure
    -0.68
     STRUCTURES
    -0.66
     Strukturen
    -0.65
     структуры
    -0.63
     Structure
    -0.63
     structures
    -0.62
     STRUCTURE
    -0.61
    structure
    -0.61
     структура
    -0.60
    струк
    -0.59
    POSITIVE LOGITS
    urally
    0.66
    urals
    0.55
    BagLayout
    0.52
    #+#
    0.46
     '\\;'
    0.45
    ural
    0.44
     betweenstory
    0.43
    IntoConstraints
    0.43
     Vikipedi
    0.43
    al
    0.42
    Act Density 0.268%

    No Known Activations