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

    Neuronpedia

    INDEX
    Explanations

    discourse markers and punctuation that indicate transitions or emphasis within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -1.05
     EconPapers
    -1.02
    CloseOperation
    -0.96
    +#+#
    -0.96
     BoxFit
    -0.90
     Савезне
    -0.89
    LookAnd
    -0.89
    AsUp
    -0.86
    DeleteBehavior
    -0.85
    uxxxx
    -0.84
    POSITIVE LOGITS
    verwijspagina
    0.68
    ↵↵↵
    0.63
    </em>
    0.61
    ↵↵
    0.55
    ↵↵↵↵
    0.55
    ↵↵↵↵↵↵
    0.54
    ↵
    0.54
     .
    0.53
     siihen
    0.50
    …
    0.50
    Act Density 1.067%

    No Known Activations