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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orer
    -0.18
    oy
    -0.15
    urlencode
    -0.15
    urr
    -0.15
    utton
    -0.15
    urg
    -0.14
    ittle
    -0.14
    ourg
    -0.14
    ῦ
    -0.14
    urga
    -0.14
    POSITIVE LOGITS
    ``
    0.17
     prere
    0.15
    _mD
    0.15
    xico
    0.14
    {:
    0.14
    kem
    0.14
    icina
    0.14
    awai
    0.14
    )")↵↵
    0.14
    echa
    0.14
    Act Density 0.168%

    No Known Activations