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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.61
     is
    -0.51
     t
    -0.48
     T
    -0.48
     “
    -0.47
     a
    -0.47
    <strong>
    -0.47
     podjet
    -0.45
    woł
    -0.44
     R
    -0.43
    POSITIVE LOGITS
     bezeichneter
    1.10
    sizeCache
    1.10
     Мексичка
    1.09
     disambiguazione
    1.07
    GEBURTSDATUM
    1.05
     ModelExpression
    1.04
    awtextra
    1.02
     AssemblyCulture
    1.02
    1.00
     betweenstory
    0.98
    Act Density 1.626%

    No Known Activations