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

    Neuronpedia

    INDEX
    Explanations

    frequency of particular spacing patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.73
    ModelBuilder
    -0.54
    saraba
    -0.53
    PostConstruct
    -0.51
     متعلقه
    -0.51
    Shady
    -0.48
    mybatisplus
    -0.48
    erring
    -0.47
     cucchiai
    -0.47
    anglès
    -0.46
    POSITIVE LOGITS
    出版年
    0.66
    RSpec
    0.63
    ьаж
    0.60
    UnsafeEnabled
    0.57
    ReusableCell
    0.56
    ércoles
    0.54
     pair
    0.47
    Identyfik
    0.46
    Pair
    0.46
     CURIAM
    0.45
    Act Density 0.326%

    No Known Activations