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

    Neuronpedia

    INDEX
    Explanations

    words related to programming languages and coding, specifically focusing on C++ and Boost libraries

    oai_token-act-pair · gpt-3.5-turbo

    instances of the Boost library in C++ code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulatory
    -0.80
     drained
    -0.78
     distracting
    -0.72
     tearing
    -0.71
     sustaining
    -0.69
    quished
    -0.68
     tort
    -0.67
     conserv
    -0.67
     restraint
    -0.67
     bursts
    -0.66
    POSITIVE LOGITS
    temp
    1.01
    operator
    0.93
    Base
    0.92
    Simple
    0.90
    Parser
    0.87
    iterator
    0.87
    NL
    0.86
    Generic
    0.86
    Raw
    0.85
    default
    0.84
    Act Density 0.008%

    No Known Activations