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

    Neuronpedia

    INDEX
    Explanations

    references to utility classes and libraries in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Finn
    -0.57
     blow
    -0.55
    mold
    -0.52
    blow
    -0.51
     Fannie
    -0.50
    Finn
    -0.48
     apartament
    -0.48
    HasForeignKey
    -0.48
     graphite
    -0.47
     LoginForm
    -0.47
    POSITIVE LOGITS
    util
    2.35
     util
    1.66
    Util
    1.45
     Util
    1.28
    UTIL
    1.23
    工具类
    1.03
     utility
    0.92
     للمعارف
    0.91
    utils
    0.91
    Utility
    0.90
    Act Density 0.017%

    No Known Activations