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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and logical structures in analytical discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isme
    -0.16
    illiseconds
    -0.15
    .experimental
    -0.15
     hala
    -0.15
    illac
    -0.15
    BOSE
    -0.15
    ObjectContext
    -0.14
     ků
    -0.14
    asin
    -0.14
    Chance
    -0.14
    POSITIVE LOGITS
     result
    0.30
     theorem
    0.29
     statement
    0.29
     property
    0.26
     results
    0.25
     properties
    0.24
    theorem
    0.23
    statement
    0.23
    ore
    0.23
     statements
    0.22
    Act Density 0.259%

    No Known Activations