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

    Neuronpedia

    INDEX
    Explanations

    references to coding or programming

    oai_token-act-pair · gpt-3.5-turbo

    references to coding and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bour
    -0.69
    Mobil
    -0.69
    bury
    -0.68
     istg
    -0.66
    Ul
    -0.65
     Dob
    -0.65
     Mutual
    -0.64
     Vaugh
    -0.63
    toggle
    -0.63
     Bru
    -0.63
    POSITIVE LOGITS
     coding
    1.29
     coded
    1.15
    anguage
    0.89
    oded
    0.88
     codes
    0.87
    oding
    0.86
    otle
    0.85
     code
    0.79
    encies
    0.78
    urated
    0.74
    Act Density 0.008%

    No Known Activations