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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ous
    -0.85
    ously
    -0.78
    vol
    -0.76
    ewitness
    -0.75
    urn
    -0.72
    vae
    -0.69
    76561
    -0.69
    lain
    -0.68
    iful
    -0.68
    bh
    -0.66
    POSITIVE LOGITS
     languages
    1.15
    matically
    1.11
     Languages
    1.06
    mers
    1.04
    mable
    0.97
    matic
    0.93
     interfaces
    0.91
     theorem
    0.87
     language
    0.85
    matical
    0.83
    Act Density 0.023%

    No Known Activations