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

    Neuronpedia

    INDEX
    Explanations

    phrases related to grammatical structure and the usage of adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оби
    -0.17
    ãĤ«ãĥ«
    -0.15
    _CT
    -0.15
    rub
    -0.14
     Duck
    -0.14
    еÑĢÑĮ
    -0.14
     Record
    -0.13
     záznam
    -0.13
    otal
    -0.13
     duck
    -0.13
    POSITIVE LOGITS
     clause
    0.27
     modifying
    0.26
     clauses
    0.24
     ger
    0.23
     Clause
    0.22
     restrictive
    0.22
     modifier
    0.22
     Modifier
    0.21
     ellipt
    0.21
     subordinate
    0.21
    Act Density 0.042%

    No Known Activations