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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Qu" and variations thereof, indicating a focus on questions or querying language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uctions
    -0.16
    вид
    -0.16
    amedi
    -0.15
    riz
    -0.14
    shield
    -0.14
    SCAN
    -0.14
    Ø´Ùħ
    -0.14
    νι
    -0.14
    ॰
    -0.14
     BIN
    -0.13
    POSITIVE LOGITS
     qu
    0.25
     Qu
    0.25
    ois
    0.19
    /qu
    0.18
    anta
    0.18
    -qu
    0.18
    attro
    0.18
     co
    0.18
    qu
    0.17
    Qu
    0.17
    Act Density 0.013%

    No Known Activations