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

    Neuronpedia

    INDEX
    Explanations

    forms of adjectives that describe qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.17
    KHR
    -0.16
    ÑģоÑĢ
    -0.15
     Zur
    -0.15
    (rawValue
    -0.15
    оби
    -0.15
    ilik
    -0.15
     Wheeler
    -0.14
     trif
    -0.14
     tá»±
    -0.14
    POSITIVE LOGITS
     ad
    0.27
     clause
    0.24
     Clause
    0.24
     clauses
    0.23
     adv
    0.21
     adjunct
    0.21
     Ad
    0.20
    Modifiers
    0.20
     modifier
    0.20
    Ad
    0.19
    Act Density 0.046%

    No Known Activations