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

    Neuronpedia

    INDEX
    Explanations

    characters and punctuation commonly used in programming and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Singleton
    -0.50
    itoria
    -0.49
    ãy
    -0.46
     tendered
    -0.46
    τηση
    -0.45
     Jaffe
    -0.45
    untut
    -0.45
     shop
    -0.45
    凈
    -0.45
    waran
    -0.45
    POSITIVE LOGITS
     autorytatywna
    1.32
    GEBURTSDATUM
    0.94
    الحياه
    0.90
     lenker
    0.89
    </strong>
    0.86
     kaarangay
    0.84
    </em>
    0.84
    </u>
    0.83
     चीज़ों
    0.82
    </h4>
    0.81
    Act Density 0.981%

    No Known Activations