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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.71
    URLException
    -0.61
    
    -0.60
    quo
    -0.57
     BoxDecoration
    -0.56
    下载附件
    -0.56
     improper
    -0.55
     TextInputType
    -0.55
    MessageTagHelper
    -0.54
    CppCodeGen
    -0.54
    POSITIVE LOGITS
     per
    0.93
     totalt
    0.73
     apiece
    0.66
    PerPage
    0.64
     totales
    0.64
     total
    0.59
     each
    0.58
     başına
    0.58
    Hentet
    0.58
    gameserver
    0.58
    Act Density 0.567%

    No Known Activations