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

    Neuronpedia

    INDEX
    Explanations

    references to proofs and theorems in mathematical or formal texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yarnpkg
    -0.56
    hibernate
    -0.49
    DotNetBar
    -0.49
     Bede
    -0.47
     ItemType
    -0.47
     Domen
    -0.44
     <<<<<<<<<<<<<<
    -0.44
    UserContext
    -0.44
     cellpadding
    -0.43
    ftagPool
    -0.43
    POSITIVE LOGITS
     proof
    2.58
     Proof
    2.52
    Proof
    2.47
    proof
    2.42
    PROOF
    2.08
     PROOF
    1.98
     proofs
    1.95
     Proofs
    1.85
     proofing
    1.68
    proofing
    1.55
    Act Density 0.187%

    No Known Activations