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

    Neuronpedia

    INDEX
    Explanations

    instances of formal proofs and citations within academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Архівовано
    -1.06
     يتيمه
    -1.04
    archiviato
    -1.00
     дописавши
    -0.99
    principalColumn
    -0.96
    Tembelea
    -0.95
    Hozzáférés
    -0.95
    Hochspringen
    -0.94
    IBOutlet
    -0.94
    日閲覧
    -0.93
    POSITIVE LOGITS
    Proof
    1.81
     Proof
    1.80
    proof
    1.79
     PROOF
    1.79
     proof
    1.75
     proofs
    1.61
    PROOF
    1.56
     Proofs
    1.42
     proofing
    1.28
    proofing
    1.06
    Act Density 0.064%

    No Known Activations