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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting signals related to academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argento
    -0.45
     gæ
    -0.45
     shooting
    -0.44
    之
    -0.43
     tæ
    -0.42
     之
    -0.41
    mentar
    -0.40
     secondaire
    -0.40
     tromper
    -0.38
    فيلم
    -0.38
    POSITIVE LOGITS
    sidemargin
    0.87
     gyhoeddwyd
    0.81
    MLLoader
    0.78
     autorytatywna
    0.75
    出版年
    0.75
    WriteTagHelper
    0.75
    twimg
    0.74
     AttributeSet
    0.72
    CppMethod
    0.71
     AssemblyCompany
    0.69
    Act Density 0.308%

    No Known Activations