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

    Neuronpedia

    INDEX
    Explanations

    references to proofs and their structure in mathematical texts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.72
     disambiguazione
    -0.71
     nahilalakip
    -0.71
    Hozzáférés
    -0.71
     חיצוניים
    -0.70
    HasForeignKey
    -0.70
     insuffisamment
    -0.69
    OGND
    -0.69
    principalColumn
    -0.69
    Tembelea
    -0.69
    POSITIVE LOGITS
     proofs
    1.01
    Proof
    0.94
    proof
    0.90
     Proofs
    0.86
     Proof
    0.85
     PROOF
    0.83
    PROOF
    0.79
     proof
    0.77
    führt
    0.69
    proofing
    0.69
    Act Density 0.039%

    No Known Activations