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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and programming-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ous
    -0.91
    ously
    -0.83
    vol
    -0.80
    lain
    -0.80
    urn
    -0.72
    ewitness
    -0.70
    lier
    -0.70
    auld
    -0.69
    same
    -0.69
    eous
    -0.69
    POSITIVE LOGITS
    mers
    1.00
    matically
    1.00
     languages
    1.00
     Languages
    0.91
    matic
    0.85
     interfaces
    0.84
    mable
    0.82
     theorem
    0.80
     programmers
    0.78
    Blocks
    0.76
    Act Density 0.027%

    No Known Activations