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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation marks in textual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.53
    ,
    -0.52
     con
    -0.45
     cre
    -0.45
     can
    -0.43
     de
    -0.43
     the
    -0.43
     cap
    -0.42
    比
    -0.41
    terna
    -0.41
    POSITIVE LOGITS
    webElementXpaths
    1.01
     ſind
    0.97
    elemField
    0.94
     iſt
    0.91
     nakalista
    0.91
     EconPapers
    0.89
     itſelf
    0.89
    findpost
    0.86
     pleaſure
    0.84
     myſelf
    0.84
    Act Density 0.414%

    No Known Activations