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

    Neuronpedia

    INDEX
    Explanations

    code-related structures and functions, particularly ones involving parsing and matching elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tur
    -0.19
     Club
    -0.16
     hyper
    -0.15
     seconds
    -0.14
     Rap
    -0.14
     Gal
    -0.14
     turf
    -0.14
     seasoning
    -0.14
     person
    -0.14
     Seconds
    -0.14
    POSITIVE LOGITS
     token
    0.28
     getToken
    0.27
     Token
    0.27
     Tokens
    0.27
     tokens
    0.26
    -token
    0.25
     TOKEN
    0.25
     Lexer
    0.25
     lexer
    0.25
     antlr
    0.24
    Act Density 0.071%

    No Known Activations