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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.98
    ,
    -0.67
    .
    -0.53
    ’
    -0.47
     in
    -0.46
     
    -0.45
    ↵↵
    -0.42
     single
    -0.40
     to
    -0.39
     “
    -0.38
    POSITIVE LOGITS
    rungsseite
    1.12
    TypedDataSet
    1.02
    SourceChecksum
    1.02
     HasFactory
    0.96
    GEBURTS
    0.94
     оригіналу
    0.94
     AssemblyTitle
    0.91
     myſelf
    0.89
     disambiguazione
    0.89
    Personendaten
    0.89
    Act Density 0.576%

    No Known Activations