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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "The"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.82
    bonjour
    -0.69
    )_/¯
    -0.66
     wikipagina
    -0.62
     EdgeInsets
    -0.59
    <bos>
    -0.59
     conformément
    -0.58
    transQ
    -0.57
     rechange
    -0.57
     semula
    -0.56
    POSITIVE LOGITS
    The
    1.21
     The
    1.15
    THE
    0.69
     AssemblyCompany
    0.67
    TypedDataSet
    0.66
     Thé
    0.62
    XMLSchema
    0.62
    An
    0.60
     THE
    0.60
     comps
    0.60
    Act Density 0.266%

    No Known Activations