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

    Neuronpedia

    INDEX
    Explanations

    apostrophes and contractions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.83
    <eos>
    -0.63
    '
    -0.63
    ‘
    -0.56
    ↵
    -0.54
     
    -0.50
    ষ্
    -0.43
    ClientRect
    -0.42
    SuppressLint
    -0.41
    <h1>
    -0.41
    POSITIVE LOGITS
    oredCriteria
    1.16
     Италијани
    1.01
     Roskov
    1.00
    Geplaatst
    0.98
    StoreMessageInfo
    0.94
    ftagPool
    0.92
     betweenstory
    0.90
    IsMutable
    0.89
     protoimpl
    0.87
    parsedMessage
    0.87
    Act Density 0.167%

    No Known Activations