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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and theorems related to proofs and properties in analytic settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     derivation
    -0.15
    ãĤ·ãĥ§ãĥ³
    -0.15
    oog
    -0.15
    .='
    -0.15
    illac
    -0.15
    ivent
    -0.15
    BuilderInterface
    -0.14
    kách
    -0.14
    retch
    -0.14
     practition
    -0.14
    POSITIVE LOGITS
     theorem
    0.23
     statement
    0.21
     characterization
    0.20
    statement
    0.20
     conservation
    0.20
    theorem
    0.20
     famous
    0.20
     properties
    0.19
     results
    0.19
     facts
    0.19
    Act Density 0.200%

    No Known Activations