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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing action or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urdy
    -0.15
    _BS
    -0.15
    usher
    -0.15
    arna
    -0.15
    anta
    -0.14
    isses
    -0.14
    uch
    -0.14
    rets
    -0.14
    ults
    -0.14
    ola
    -0.14
    POSITIVE LOGITS
     to
    0.25
    ä¸ĭåİ»
    0.17
    ="{!!
    0.16
    azen
    0.15
    ble
    0.14
    تا
    0.14
    obot
    0.14
    Vtbl
    0.14
    857
    0.14
    871
    0.14
    Act Density 0.034%

    No Known Activations