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

    Neuronpedia

    INDEX
    Explanations

    references to literals in programming or markup languages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    #+#
    -1.21
    ChildScrollView
    -1.12
     Савезне
    -1.05
     الرياضيه
    -0.99
    adaptiveStyles
    -0.99
    AddTagHelper
    -0.98
    IUrlHelper
    -0.98
     EconPapers
    -0.94
     CreateTagHelper
    -0.94
     متعلقه
    -0.92
    POSITIVE LOGITS
     
    0.50
     numériques
    0.45
     herein
    0.42
    duga
    0.40
     ho
    0.39
     literals
    0.39
    literal
    0.39
     $
    0.39
     Ho
    0.38
     candidat
    0.38
    Act Density 0.010%

    No Known Activations