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

    Neuronpedia

    INDEX
    Explanations

    various forms of quotation marks and related punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.86
     houſe
    -0.76
     EconPapers
    -0.76
    ScopeManager
    -0.71
    featureID
    -0.71
     Савезне
    -0.69
    ItemBackground
    -0.68
     chi̍t
    -0.68
    nalités
    -0.67
    EndContext
    -0.67
    POSITIVE LOGITS
    </code>
    0.53
    "
    0.50
    </i>
    0.44
    ・「
    0.44
    ”
    0.43
    ParallelGroup
    0.43
    false
    0.43
    ",
    0.42
    name
    0.41
    '
    0.41
    Act Density 0.458%

    No Known Activations