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

    Neuronpedia

    INDEX
    Explanations

    high-frequency function words and grammatical constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIX
    -0.16
     hayır
    -0.16
    ollect
    -0.14
    izik
    -0.14
    RULE
    -0.14
    atter
    -0.14
    رÛĮز
    -0.14
    é³´
    -0.14
    employment
    -0.14
    BaseContext
    -0.14
    POSITIVE LOGITS
    uco
    0.19
    ucken
    0.15
     throughout
    0.15
     normal
    0.15
    essional
    0.15
    -normal
    0.15
    con
    0.14
    L
    0.14
    elho
    0.14
    q
    0.14
    Act Density 0.000%

    No Known Activations