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

    Neuronpedia

    INDEX
    Explanations

    comparisons using the word "as" followed by a noun phrase

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     hoga
    -0.76
     karna
    -0.73
     kade
    -0.71
     gmbh
    -0.68
     saha
    -0.68
     bera
    -0.68
     labd
    -0.68
    ervations
    -0.66
     sirup
    -0.65
     jawa
    -0.65
    POSITIVE LOGITS
     as
    0.80
     As
    0.77
    as
    0.73
    Să
    0.68
     AS
    0.68
    As
    0.68
    Și
    0.67
    Sebagai
    0.65
    <bos>
    0.63
     étroite
    0.59
    Act Density 0.266%

    No Known Activations