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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and terms related to theorems and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isme
    -0.17
    .experimental
    -0.16
    ãĤ·ãĥ§ãĥ³
    -0.16
     derivation
    -0.15
    aise
    -0.15
    hani
    -0.15
    umat
    -0.14
    ElementException
    -0.14
    ancock
    -0.14
    ellar
    -0.14
    POSITIVE LOGITS
     theorem
    0.30
     law
    0.29
     conservation
    0.28
     Conservation
    0.26
    theorem
    0.26
     identities
    0.25
     Law
    0.24
     identity
    0.24
    law
    0.24
     statement
    0.23
    Act Density 0.198%

    No Known Activations