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

    Neuronpedia

    INDEX
    Explanations

    the presence and frequency of the phrase "we're."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etter
    -0.18
    ucas
    -0.17
    obao
    -0.16
    asures
    -0.15
    ether
    -0.15
    -Core
    -0.14
    à¸Ńà¸Ķ
    -0.14
    aurus
    -0.14
    resident
    -0.14
    ãĤ¯ãĤ»
    -0.14
    POSITIVE LOGITS
    oran
    0.15
    onces
    0.14
    pattern
    0.14
     Dann
    0.14
    imore
    0.14
    .EventQueue
    0.14
    zeÅĦ
    0.14
    ман
    0.14
    agnar
    0.14
    blade
    0.14
    Act Density 0.026%

    No Known Activations