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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.62
    graham
    -0.59
    Чу
    -0.57
     petra
    -0.55
     Cocoa
    -0.54
    rungsseite
    -0.54
     Chwiliwch
    -0.54
    mazaki
    -0.52
    Джерела
    -0.52
    ReusableCell
    -0.52
    POSITIVE LOGITS
    ,”
    0.88
    ,"
    0.84
    ,’”
    0.82
    ，”
    0.81
    ="<?=$
    0.77
    ),"
    0.76
     <=",
    0.75
    ",$
    0.74
    ),”
    0.72
    ,'"
    0.72
    Act Density 0.039%

    No Known Activations