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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities and proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.51
     vzd
    -0.50
     flavors
    -0.46
    currPos
    -0.45
    таратура
    -0.44
    出版年
    -0.43
    ͓
    -0.43
     XE
    -0.43
    лади
    -0.43
    kmäler
    -0.43
    POSITIVE LOGITS
     AssemblyTitle
    0.81
    ंदीखरीदारी
    0.69
     Amongst
    0.69
    IndentedString
    0.69
    parametrize
    0.69
    êncio
    0.68
     HttpStatusCode
    0.68
     amongst
    0.66
     autorytatywna
    0.65
    脚注の使い方
    0.65
    Act Density 0.032%

    No Known Activations