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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.78
     "..\..\..\
    -0.77
     GenerationType
    -0.77
    TestingModule
    -0.74
    SourceChecksum
    -0.69
     EconPapers
    -0.68
    はじめに
    -0.67
    Życiorys
    -0.66
    BeginContext
    -0.66
     Réponses
    -0.64
    POSITIVE LOGITS
    complexContent
    0.53
    ApiProperty
    0.49
    rawdę
    0.45
     honestly
    0.44
    Inflater
    0.42
     classNames
    0.41
     kiệm
    0.41
     fej
    0.41
    ٫
    0.41
     fronte
    0.40
    Act Density 0.819%

    No Known Activations