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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their relationships to the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ứng
    -0.09
    xDB
    -0.09
     mastur
    -0.09
    ’ta
    -0.09
    ’na
    -0.09
    AZY
    -0.09
     Ãľst
    -0.08
    'na
    -0.08
    madan
    -0.08
    ÏĩεδÏĮν
    -0.08
    POSITIVE LOGITS
     etc
    0.08
    0.07
    Ī
    0.07
    ace
    0.06
     (
    0.06
     l
    0.06
    o
    0.06
    anna
    0.05
     em
    0.05
    ito
    0.05
    Act Density 0.034%

    No Known Activations