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

    Neuronpedia

    INDEX
    Explanations

    keywords related to syntax and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to programming syntax and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kore
    -0.79
     Gunn
    -0.76
     Gund
    -0.74
    zona
    -0.73
     Fors
    -0.71
    agher
    -0.69
    male
    -0.69
    ECD
    -0.68
    oppable
    -0.68
     Kong
    -0.68
    POSITIVE LOGITS
     syntax
    1.15
    ntax
    1.05
     highlighting
    0.94
     notation
    0.88
     translation
    0.87
    hess
    0.87
     substitution
    0.85
     keywords
    0.83
     parsing
    0.81
     definitions
    0.81
    Act Density 0.020%

    No Known Activations