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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walton
    -0.15
    Hints
    -0.14
    cak
    -0.14
     Atl
    -0.14
    Specifier
    -0.13
     Bren
    -0.13
    *scale
    -0.13
    ompiler
    -0.13
    Volume
    -0.13
     tham
    -0.13
    POSITIVE LOGITS
     corpor
    0.24
     word
    0.24
     frequencies
    0.24
     glove
    0.23
     frequency
    0.23
     Corpor
    0.23
     corpus
    0.22
     Token
    0.22
     token
    0.21
    /doc
    0.21
    Act Density 0.055%

    No Known Activations